From 22cd26f75da5e43257b4d4b385a335c5bae0256e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Gabriel=20Pereira=20G=C3=B3es?= <82218878+Dspofu@users.noreply.github.com> Date: Thu, 2 Jul 2026 13:06:39 -0300 Subject: [PATCH] feat: Implementation of the Portuguese (Brazil) language and VRAM/RAM monitor (#6509) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * feat: Implementation of the Portuguese (Brazil) language and VRAM/RAM monitor. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update studio/frontend/src/hooks/use-gpu-utilization.ts Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update studio/backend/main.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update studio/backend/main.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update studio/backend/utils/hardware/hardware.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update studio/backend/utils/hardware/hardware.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update studio/frontend/src/features/settings/components/usage-examples.tsx Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update studio/backend/main.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update studio/backend/utils/hardware/hardware.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update studio/frontend/src/features/studio/sections/progress-section.tsx Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * fix: resolve automated review feedback on API shape * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix review issues for PR #6509: Cpu icon, VRAM percent, system polling - model-inspector: use the exported CpuIcon (Cpu is not a Hugeicons export) - app-sidebar: guard the VRAM percent on totalVram to avoid Infinity, and reset the system poll cache only after each request settles so a slow probe is reused instead of stacking overlapping requests - use-gpu-info: populate CPU/RAM on hosts without a GPU - progress-section: label GPUs by visible_ordinal instead of array index - hub-page: base the RAM label on systemRamTotalGb - usage-examples: emit JS sampling and tool options at the top level instead of nesting them under extra_body (the JS SDK does not unwrap extra_body) - main: read torch and transformers versions from package metadata instead of importing the libraries on every system poll, and guard the VRAM math against null values - hardware: translate a leftover comment to English * Harden /api/system: guard psutil.boot_time for PR #6509 Simulating restricted containers and some VMs (where psutil.boot_time can raise) showed the /api/system endpoint would 500 on the unguarded boot_time call, the same failure class already handled for cpu_freq, disk_usage, and Process. Wrap boot_time and return uptime_seconds as null when it is unavailable so the sidebar monitor degrades gracefully instead of breaking. Widen the uptime_seconds type to number | null to match. * Studio: make the sidebar hardware monitor a toggle (default on) for PR #6509 Adds a "Show hardware monitor" switch under Settings > Appearance > Layout, backed by a localStorage preference (default on), mirroring the existing useSidebarPin pattern. When turned off, the sidebar hides the VRAM/RAM meters and useSystemInfo stops the 3s /api/system poll entirely, so no nvidia-smi / SMI probes run while the monitor is disabled. Adds the en and pt-BR strings. * Studio: default the sidebar hardware monitor to off (opt-in) for PR #6509 * Studio pt-BR: fix three small translation defects for PR #6509 - learningRateDescription: "5e-5 for CPT" -> "5e-5 para CPT" (leftover English) - exportScopeRecents: "Recents" -> "Recentes" (untranslated) - relativeMonthsAgo/relativeYearsAgo: add the missing space ("há {count} meses"/ "há {count} anos") so they no longer render as "há 3meses" * Studio pt-BR: translate the last 10 fallback keys for PR #6509 Adds the settings.general.storage block (Armazenamento) and the settings.chat.modelDisclaimer pair, so pt-BR now covers all en keys (679/679) with no English fallbacks. * Studio: hide sidebar VRAM row on CPU-only hosts for PR #6509 * Studio: tighten and trim code comments for PR #6509 * fix: UI issue in the stop button dialog box (fine-tuning) * Studio pt-BR: translate 18 new keys from main merge (password dialog, GGUF export, dataset streaming) for PR #6509 * Rounding to GB * Fix/adjust System resources tab for PR #6509 * Fix/adjust GPU monitor review items for PR #6509 * Fix/adjust remaining GPU monitor review items for PR #6509 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix/adjust MLX resource fallback for PR #6509 * floating window implementation * resize for floating window * Fix resource monitor review items * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Restore frontend optional dependency lock entries * Make GPU selection tests hermetic * Fix GPU monitor CI test failures * Bound MLX GGUF reload smoke * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix MLX GGUF reload smoke exit --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Daniel Han Co-authored-by: wasimysaid --- studio/backend/main.py | 131 ++- .../backend/tests/test_anthropic_messages.py | 8 +- studio/backend/tests/test_gpu_selection.py | 231 ++++- studio/backend/utils/hardware/hardware.py | 272 +++-- .../src/components/floating-monitor.tsx | 160 +++ .../features/hub/catalog/models-header.tsx | 6 +- studio/frontend/src/features/hub/hub-page.tsx | 11 +- .../settings/components/usage-examples.tsx | 149 ++- .../src/features/settings/settings-dialog.tsx | 208 ++-- .../settings/stores/monitor-overlay-store.ts | 24 + .../settings/stores/settings-dialog-store.ts | 2 + .../features/settings/tabs/general-tab.tsx | 1 + .../features/settings/tabs/resources-tab.tsx | 477 +++++++++ .../studio/sections/progress-section.tsx | 128 ++- studio/frontend/src/hooks/index.ts | 2 + studio/frontend/src/hooks/use-gpu-info.ts | 47 +- .../frontend/src/hooks/use-gpu-utilization.ts | 6 +- studio/frontend/src/hooks/use-system.ts | 130 +++ studio/frontend/src/i18n/AGENTS.md | 3 +- studio/frontend/src/i18n/check-parity.ts | 6 +- studio/frontend/src/i18n/locales/en.ts | 55 ++ studio/frontend/src/i18n/locales/pt-br.ts | 934 ++++++++++++++++++ studio/frontend/src/i18n/messages.ts | 13 +- tests/studio/install/test_rocm_support.py | 6 +- tests/studio/run_real_mlx_smoke.py | 66 +- 25 files changed, 2691 insertions(+), 385 deletions(-) create mode 100644 studio/frontend/src/components/floating-monitor.tsx create mode 100644 studio/frontend/src/features/settings/stores/monitor-overlay-store.ts create mode 100644 studio/frontend/src/features/settings/tabs/resources-tab.tsx create mode 100644 studio/frontend/src/hooks/use-system.ts create mode 100644 studio/frontend/src/i18n/locales/pt-br.ts diff --git a/studio/backend/main.py b/studio/backend/main.py index 5402e5eb7b..0613a5ae53 100644 --- a/studio/backend/main.py +++ b/studio/backend/main.py @@ -12,6 +12,8 @@ from pathlib import Path as _Path import asyncio from dataclasses import asdict +from typing import Any, Optional + # Suppress C-level dependency warnings globally os.environ["PYTHONWARNINGS"] = "ignore" @@ -36,6 +38,10 @@ if sys.platform == "win32": pass del _win_stream +_SYSTEM_GPU_CACHE_TTL_SECONDS = 10.0 +_system_gpu_cache_lock = threading.Lock() +_system_gpu_cache: Optional[tuple[float, dict[str, Any]]] = None + # ── Windows AMD ROCm DLL injection ────────────────────────────────────────── # Python 3.8+ ignores PATH for extension modules; register ROCm bin dirs with # os.add_dll_directory() so amdhip64.dll etc. are found before any torch import. @@ -226,7 +232,6 @@ import shutil import warnings from contextlib import asynccontextmanager from importlib.metadata import PackageNotFoundError, version as package_version -from typing import Optional from urllib.parse import urlparse @@ -1078,8 +1083,57 @@ async def shutdown_server(request: Request, current_subject: str = Depends(get_c return {"status": "shutting_down"} +def _get_cached_system_gpu_info(logger) -> dict[str, Any]: + """Return merged GPU visibility/utilization with bounded live-probe churn.""" + import time + from utils.hardware import get_backend_visible_gpu_info, get_visible_gpu_utilization + + global _system_gpu_cache + now = time.monotonic() + with _system_gpu_cache_lock: + if _system_gpu_cache is not None: + cached_at, cached_gpu_info = _system_gpu_cache + if now - cached_at < _SYSTEM_GPU_CACHE_TTL_SECONDS: + return cached_gpu_info + + try: + visibility_info = get_backend_visible_gpu_info() or {"available": False, "devices": []} + except Exception as e: + logger.debug(f"Failed to get GPU visibility info: {e}") + visibility_info = {"available": False, "devices": []} + + try: + utilization_info = get_visible_gpu_utilization() or {"devices": []} + except Exception as e: + logger.debug(f"Failed to get GPU utilization info: {e}") + utilization_info = {"devices": []} + + util_devices = {d.get("index"): d for d in utilization_info.get("devices", [])} + enriched_devices = [] + + for dev in visibility_info.get("devices", []): + idx = dev.get("index") + util = util_devices.get(idx, {}) + + total_vram = util.get("vram_total_gb") or dev.get("memory_total_gb") or 0 + used_vram = util.get("vram_used_gb") or 0 + + enriched_dev = dict(dev) + enriched_dev["vram_used_gb"] = used_vram + enriched_dev["vram_free_gb"] = round(total_vram - used_vram, 2) if total_vram else 0 + enriched_dev["vram_utilization_pct"] = util.get("vram_utilization_pct") + enriched_devices.append(enriched_dev) + + gpu_info = { + "available": visibility_info.get("available", False), + "devices": enriched_devices, + } + _system_gpu_cache = (time.monotonic(), gpu_info) + return gpu_info + + @app.get("/api/system") -async def get_system_info(current_subject: str = Depends(get_current_subject)): +def get_system_info(current_subject: str = Depends(get_current_subject)): """Get system information. Auth-gated: the response (platform, Python/GPU, memory, ML packages) can @@ -1088,31 +1142,82 @@ async def get_system_info(current_subject: str = Depends(get_current_subject)): """ import platform import psutil + import os + import time + import logging from utils.hardware import get_device from utils.hardware.hardware import _backend_label - visibility_info = get_backend_visible_gpu_info() - gpu_info = { - "available": visibility_info["available"], - "devices": visibility_info["devices"], - } + logger = logging.getLogger(__name__) + + gpu_info = _get_cached_system_gpu_info(logger) - # CPU & Memory memory = psutil.virtual_memory() + try: + cpu_freq = psutil.cpu_freq() + except Exception as e: + logger.debug(f"Failed to get CPU frequency: {e}") + cpu_freq = None + + try: + disk = psutil.disk_usage(os.path.abspath(os.sep)) + except Exception as e: + logger.debug(f"Failed to get disk usage: {e}") + disk = None + + try: + current_process = psutil.Process(os.getpid()) + process_used_mb = round(current_process.memory_info().rss / 1024**2) + except Exception as e: + logger.debug(f"Failed to get current process memory: {e}") + process_used_mb = 0 + + try: + boot_time = psutil.boot_time() + except Exception as e: + logger.debug(f"Failed to get boot time: {e}") + boot_time = None + + # Read versions from metadata so a 3s poll never imports heavy ML libs (or 500s on their import errors). + from importlib.metadata import PackageNotFoundError, version as pkg_version + + ml_packages = {} + for pkg in ("torch", "transformers"): + try: + ml_packages[pkg] = pkg_version(pkg) + except PackageNotFoundError: + pass + except Exception as e: + logger.debug(f"Failed to read {pkg} version: {e}") + return { "platform": platform.platform(), "python_version": platform.python_version(), - # _backend_label so /api/system reports "rocm" (not "cuda") on AMD, - # matching /api/hardware and /api/gpu-visibility. "device_backend": _backend_label(get_device()), - "cpu_count": psutil.cpu_count(), + "cpu_count": psutil.cpu_count(logical = True), + "uptime_seconds": max(0, round(time.time() - boot_time)) if boot_time else None, + "cpu": { + "logical_count": psutil.cpu_count(logical = True), + "physical_count": psutil.cpu_count(logical = False), + "usage_percent": psutil.cpu_percent(interval = None), + "frequency_mhz": round(cpu_freq.current, 2) + if cpu_freq and cpu_freq.current is not None + else None, + }, "memory": { - "total_gb": round(memory.total / 1e9, 2), - "available_gb": round(memory.available / 1e9, 2), + "total_gb": round(memory.total / 1024**3, 2), + "available_gb": round(memory.available / 1024**3, 2), "percent_used": memory.percent, + "process_used_mb": process_used_mb, + }, + "disk": { + "total_gb": round(disk.total / 1e9, 2) if disk else 0, + "free_gb": round(disk.free / 1e9, 2) if disk else 0, + "percent_used": disk.percent if disk else 0, }, "gpu": gpu_info, + "ml_packages": ml_packages, } diff --git a/studio/backend/tests/test_anthropic_messages.py b/studio/backend/tests/test_anthropic_messages.py index 92a87ce045..a6c1fcda9c 100644 --- a/studio/backend/tests/test_anthropic_messages.py +++ b/studio/backend/tests/test_anthropic_messages.py @@ -128,13 +128,7 @@ class TestToolActionNudge: assert "call render_html once" in nudge def test_balanced_nudge_empty_without_known_tool_categories(self): - assert ( - _build_tool_action_nudge( - tools = [], - model_name = "Llama-3.1-8B-Instruct", - ) - == "" - ) + assert _build_tool_action_nudge(tools = [], model_name = "Llama-3.1-8B-Instruct") == "" # ===================================================================== diff --git a/studio/backend/tests/test_gpu_selection.py b/studio/backend/tests/test_gpu_selection.py index d96f88e4a6..69ad560788 100644 --- a/studio/backend/tests/test_gpu_selection.py +++ b/studio/backend/tests/test_gpu_selection.py @@ -5,9 +5,11 @@ import asyncio import importlib.util import os import re +import sys import unittest +from contextlib import nullcontext from pathlib import Path -from types import SimpleNamespace +from types import ModuleType, SimpleNamespace from unittest.mock import patch from fastapi import HTTPException @@ -22,6 +24,7 @@ from utils.hardware import ( estimate_required_model_memory_gb, get_backend_visible_gpu_info, get_device_map, + get_gpu_utilization, get_offloaded_device_map_entries, get_parent_visible_gpu_ids, get_visible_gpu_utilization, @@ -33,6 +36,24 @@ import utils.hardware.hardware as _hw_module _BACKEND_ROOT = Path(__file__).resolve().parent.parent +async def _inline_to_thread(func, /, *args, **kwargs): + return func(*args, **kwargs) + + +def _fake_unsloth_attention_modules(resolver): + unsloth_module = ModuleType("unsloth") + models_module = ModuleType("unsloth.models") + utils_module = ModuleType("unsloth.models._utils") + utils_module.resolve_attention_implementation = resolver + models_module._utils = utils_module + unsloth_module.models = models_module + return { + "unsloth": unsloth_module, + "unsloth.models": models_module, + "unsloth.models._utils": utils_module, + } + + def _load_route_module(name: str, relative_path: str): spec = importlib.util.spec_from_file_location(name, _BACKEND_ROOT / relative_path) module = importlib.util.module_from_spec(spec) @@ -122,6 +143,139 @@ class TestResolveRequestedGpuIds(_GpuCacheResetMixin, unittest.TestCase): class TestVisibleGpuUtilization(_GpuCacheResetMixin, unittest.TestCase): + def test_gpu_utilization_preserves_primary_shape_with_devices(self): + devices = [ + { + "index": 5, + "visible_ordinal": 0, + "gpu_utilization_pct": 11.0, + "temperature_c": 40.0, + "vram_used_gb": 4.0, + "vram_total_gb": 24.0, + "vram_utilization_pct": 16.7, + "power_draw_w": 80.0, + "power_limit_w": 300.0, + "power_utilization_pct": 26.7, + }, + { + "index": 3, + "visible_ordinal": 1, + "gpu_utilization_pct": 22.0, + "temperature_c": 50.0, + "vram_used_gb": 8.0, + "vram_total_gb": 24.0, + "vram_utilization_pct": 33.3, + "power_draw_w": 120.0, + "power_limit_w": 300.0, + "power_utilization_pct": 40.0, + }, + ] + + with ( + patch("utils.hardware.hardware.get_device", return_value = DeviceType.CUDA), + patch.object(_hw_module, "IS_ROCM", False), + patch( + "utils.hardware.hardware._get_parent_visible_gpu_spec", + return_value = {"raw": "5,3", "numeric_ids": [5, 3]}, + ), + patch( + "utils.hardware.hardware._smi_query", + return_value = { + "available": True, + "devices": devices, + "backend_cuda_visible_devices": "5,3", + "parent_visible_gpu_ids": [5, 3], + "index_kind": "physical", + }, + ), + ): + result = get_gpu_utilization() + + self.assertIsInstance(result, dict) + self.assertTrue(result["available"]) + self.assertEqual(result["backend"], "cuda") + self.assertEqual(result["index"], 5) + self.assertEqual(result["visible_ordinal"], 0) + self.assertEqual(result["vram_total_gb"], 24.0) + self.assertEqual(result["parent_visible_gpu_ids"], [5, 3]) + self.assertEqual([device["index"] for device in result["devices"]], [5, 3]) + + def test_gpu_utilization_cpu_returns_legacy_unavailable_object(self): + with patch("utils.hardware.hardware.get_device", return_value = DeviceType.CPU): + result = get_gpu_utilization() + + self.assertEqual(result, {"available": False, "backend": "cpu", "devices": []}) + + def test_gpu_utilization_mlx_stays_available_without_agx_stats(self): + fake_psutil = ModuleType("psutil") + fake_psutil.virtual_memory = lambda: SimpleNamespace(total = 64 * 1024**3) + + with ( + patch.dict(sys.modules, {"psutil": fake_psutil}), + patch("utils.hardware.hardware.get_device", return_value = DeviceType.MLX), + patch("utils.hardware.hardware._read_apple_gpu_stats", return_value = {}), + patch( + "core.training.get_training_backend", + return_value = SimpleNamespace(_progress = None), + ), + patch("utils.hardware.apple.read_gpu_temperature_c", return_value = None), + patch("utils.hardware.apple.read_gpu_power_w", return_value = None), + ): + result = get_gpu_utilization() + + self.assertTrue(result["available"]) + self.assertEqual(result["backend"], "mlx") + self.assertIsNone(result["gpu_utilization_pct"]) + self.assertEqual(result["vram_used_gb"], 0) + self.assertEqual(result["vram_total_gb"], 64.0) + self.assertEqual(len(result["devices"]), 1) + + def test_gpu_utilization_xpu_uses_visible_devices(self): + with ( + patch("utils.hardware.hardware.get_device", return_value = DeviceType.XPU), + patch( + "utils.hardware.hardware.get_visible_gpu_utilization", + return_value = { + "available": True, + "backend": "xpu", + "parent_visible_gpu_ids": [2, 0], + "index_kind": "physical", + "devices": [ + { + "index": 2, + "visible_ordinal": 1, + "gpu_utilization_pct": None, + "temperature_c": None, + "vram_used_gb": 3.0, + "vram_total_gb": 16.0, + "vram_utilization_pct": 18.8, + "power_draw_w": None, + "power_limit_w": None, + "power_utilization_pct": None, + }, + { + "index": 0, + "visible_ordinal": 0, + "gpu_utilization_pct": None, + "temperature_c": None, + "vram_used_gb": 1.0, + "vram_total_gb": 16.0, + "vram_utilization_pct": 6.3, + "power_draw_w": None, + "power_limit_w": None, + "power_utilization_pct": None, + }, + ], + }, + ), + ): + result = get_gpu_utilization() + + self.assertEqual(result["backend"], "xpu") + self.assertEqual(result["index"], 0) + self.assertEqual(result["visible_ordinal"], 0) + self.assertEqual([device["index"] for device in result["devices"]], [0, 2]) + def test_visible_gpu_utilization_filters_to_parent_visible_ids(self): smi_output = "\n".join( [ @@ -272,6 +426,14 @@ class TestGpuAutoSelection(_GpuCacheResetMixin, unittest.TestCase): def test_get_offloaded_device_map_entries_handles_models_without_device_map(self): self.assertEqual(get_offloaded_device_map_entries(SimpleNamespace()), {}) + @patch( + "utils.hardware.hardware._resolve_model_identifier_for_gpu_estimate", + new = lambda model_name, **_: model_name, + ) + @patch( + "utils.hardware.hardware._load_config_for_gpu_estimate", + new = lambda *_args, **_kwargs: None, + ) def test_estimate_required_memory_formulas(self): eight_gb = 8 * (1024**3) @@ -432,6 +594,7 @@ class TestGpuAutoSelection(_GpuCacheResetMixin, unittest.TestCase): def test_prepare_gpu_selection_preserves_explicit_ids_without_auto_selection(self): with ( + patch("utils.hardware.hardware.get_device", return_value = DeviceType.CUDA), patch( "utils.hardware.hardware.resolve_requested_gpu_ids", return_value = [2, 3], @@ -464,6 +627,7 @@ class TestGpuAutoSelection(_GpuCacheResetMixin, unittest.TestCase): def test_prepare_gpu_selection_preserves_uuid_parent_visibility_in_auto_mode(self): with ( patch.dict(os.environ, {"CUDA_VISIBLE_DEVICES": "GPU-aaa,GPU-bbb"}, clear = True), + patch("utils.hardware.hardware.get_device", return_value = DeviceType.CUDA), patch( "utils.hardware.hardware.estimate_required_model_memory_gb", return_value = ( @@ -582,6 +746,7 @@ class TestPreSpawnGpuResolution(_GpuCacheResetMixin, unittest.TestCase): with ( patch.dict(os.environ, {"CUDA_VISIBLE_DEVICES": "GPU-aaa,GPU-bbb"}, clear = True), + patch("utils.hardware.hardware.get_device", return_value = DeviceType.CUDA), patch( "core.training.training._CTX.Queue", side_effect = [dummy_queue, dummy_queue], @@ -709,14 +874,23 @@ class TestRouteErrors(unittest.TestCase): has_audio_input = False, ) - with patch.object( - inference_route.ModelConfig, - "from_identifier", - return_value = model_config, + with ( + patch.object( + inference_route, + "ModelConfig", + SimpleNamespace(from_identifier = lambda **_kwargs: model_config), + ), + patch.object( + inference_route, + "_guard_chat_load_against_training", + return_value = None, + ), + patch.object(inference_route.asyncio, "to_thread", new = _inline_to_thread), + patch.object(inference_route, "_hf_offline_if_dns_dead", nullcontext), ): with self.assertRaises(HTTPException) as exc_info: asyncio.run( - inference_route.load_model( + inference_route._load_model_impl( request, SimpleNamespace( app = SimpleNamespace( @@ -835,9 +1009,9 @@ class TestRouteErrors(unittest.TestCase): with ( patch.object( - inference_route.ModelConfig, - "from_identifier", - return_value = model_config, + inference_route, + "ModelConfig", + SimpleNamespace(from_identifier = lambda **_kwargs: model_config), ), patch.object( inference_route, @@ -849,6 +1023,13 @@ class TestRouteErrors(unittest.TestCase): "get_llama_cpp_backend", return_value = SimpleNamespace(is_loaded = False), ), + patch.object( + inference_route, + "_guard_chat_load_against_training", + return_value = None, + ), + patch.object(inference_route.asyncio, "to_thread", new = _inline_to_thread), + patch.object(inference_route, "_hf_offline_if_dns_dead", nullcontext), patch( "core.export.get_export_backend", return_value = SimpleNamespace(current_checkpoint = None), @@ -856,7 +1037,7 @@ class TestRouteErrors(unittest.TestCase): ): with self.assertRaises(HTTPException) as exc_info: asyncio.run( - inference_route.load_model( + inference_route._load_model_impl( request, SimpleNamespace( app = SimpleNamespace( @@ -899,9 +1080,9 @@ class TestRouteErrors(unittest.TestCase): with ( patch.object( - inference_route.ModelConfig, - "from_identifier", - return_value = model_config, + inference_route, + "ModelConfig", + SimpleNamespace(from_identifier = lambda **_kwargs: model_config), ), patch.object( inference_route, @@ -913,6 +1094,13 @@ class TestRouteErrors(unittest.TestCase): "get_llama_cpp_backend", return_value = SimpleNamespace(is_loaded = False), ), + patch.object( + inference_route, + "_guard_chat_load_against_training", + return_value = None, + ), + patch.object(inference_route.asyncio, "to_thread", new = _inline_to_thread), + patch.object(inference_route, "_hf_offline_if_dns_dead", nullcontext), patch( "core.export.get_export_backend", return_value = SimpleNamespace(current_checkpoint = None), @@ -920,7 +1108,7 @@ class TestRouteErrors(unittest.TestCase): ): with self.assertRaises(HTTPException) as exc_info: asyncio.run( - inference_route.load_model( + inference_route._load_model_impl( request, SimpleNamespace( app = SimpleNamespace( @@ -1102,10 +1290,7 @@ class TestPerGpuFitGuardAllCounts(unittest.TestCase): cfg._attn_implementation = "eager" return "eager" - with patch( - "unsloth.models._utils.resolve_attention_implementation", - side_effect = _stub_resolver, - ): + with patch.dict(sys.modules, _fake_unsloth_attention_modules(_stub_resolver)): hardware_module._determine_attention_impl_for_gpu_estimate(config) self.assertFalse(hasattr(config, "_attn_implementation")) @@ -1133,10 +1318,7 @@ class TestPerGpuFitGuardAllCounts(unittest.TestCase): with ( patch.object(AutoModelForCausalLM, "_model_mapping", new = None), patch.object(AutoModel, "_model_mapping", new = None), - patch( - "unsloth.models._utils.resolve_attention_implementation", - side_effect = _stub_resolver, - ), + patch.dict(sys.modules, _fake_unsloth_attention_modules(_stub_resolver)), ): result = hardware_module._determine_attention_impl_for_gpu_estimate(config) @@ -1173,10 +1355,7 @@ class TestPerGpuFitGuardAllCounts(unittest.TestCase): inner._attn_implementation = "eager" return "eager" - with patch( - "unsloth.models._utils.resolve_attention_implementation", - side_effect = _stub_resolver, - ): + with patch.dict(sys.modules, _fake_unsloth_attention_modules(_stub_resolver)): hardware_module._determine_attention_impl_for_gpu_estimate(config) self.assertFalse(hasattr(config, "_attn_implementation")) diff --git a/studio/backend/utils/hardware/hardware.py b/studio/backend/utils/hardware/hardware.py index 88a1784b88..cde7070075 100644 --- a/studio/backend/utils/hardware/hardware.py +++ b/studio/backend/utils/hardware/hardware.py @@ -710,82 +710,159 @@ def _rocm_windows_perf_counter_vram_gb() -> tuple[Optional[float], Optional[floa return None, None +def _gpu_utilization_payload( + device: DeviceType, devices: list[Dict[str, Any]], **metadata: Any +) -> Dict[str, Any]: + """Keep the legacy primary-GPU shape and append all visible devices.""" + backend = _backend_label(device) + normalized = [] + for ordinal, raw in enumerate(devices): + dev = dict(raw) + dev.setdefault("available", True) + dev.setdefault("backend", backend) + if dev.get("visible_ordinal") is None: + dev["visible_ordinal"] = ordinal + normalized.append(dev) + + normalized.sort(key = lambda dev: dev.get("visible_ordinal", dev.get("index", 0))) + payload: Dict[str, Any] = { + "available": bool(normalized), + "backend": backend, + "devices": normalized, + } + payload.update(metadata) + if normalized: + payload.update(normalized[0]) + payload["available"] = True + payload["backend"] = normalized[0].get("backend", backend) + payload["devices"] = normalized + return payload + + def get_gpu_utilization() -> Dict[str, Any]: - """Return a live snapshot of device utilization information.""" + """Live utilization snapshot for the primary GPU plus all visible GPUs.""" device = get_device() + if device == DeviceType.XPU: + result = get_visible_gpu_utilization() + return _gpu_utilization_payload( + device, + result.get("devices", []), + parent_visible_gpu_ids = result.get("parent_visible_gpu_ids", []), + index_kind = result.get("index_kind"), + ) + if device == DeviceType.CUDA: - result = _smi_query("get_primary_gpu_utilization") - if result is not None: - result["backend"] = _backend_label(device) - if IS_ROCM: - # Fix unified-memory VRAM on AMD iGPUs (Strix Halo etc.). - _reconcile_primary_rocm_unified_memory(result, _get_parent_visible_gpu_spec()) - return result - # SMI unavailable. On Windows, use Performance Counters (Task Manager - # source) for system-wide VRAM, covering cross-process usage torch can't see. + parent_visible_spec = _get_parent_visible_gpu_spec() + result = _smi_query( + "get_visible_gpu_utilization", + parent_visible_spec["numeric_ids"], + parent_cuda_visible_devices = parent_visible_spec["raw"], + ) + if result is not None and "devices" in result: + devices = result["devices"] + numeric_ids = parent_visible_spec.get("numeric_ids") + if IS_ROCM and numeric_ids is not None: + _reconcile_rocm_unified_memory(result, numeric_ids) + + return _gpu_utilization_payload( + device, + devices, + backend_cuda_visible_devices = result.get("backend_cuda_visible_devices"), + parent_visible_gpu_ids = result.get("parent_visible_gpu_ids", []), + index_kind = result.get("index_kind"), + ) + + # Fallback Windows ROCm if IS_ROCM and platform.system() == "Windows": _win_used, _win_total = _rocm_windows_perf_counter_vram_gb() if _win_used is not None and _win_total is not None: _win_util = _rocm_windows_perf_counter_gpu_util_pct() - return { - "available": True, - "backend": _backend_label(device), - "gpu_utilization_pct": _win_util, - "temperature_c": None, - "vram_used_gb": _win_used, - "vram_total_gb": _win_total, - "vram_utilization_pct": round((_win_used / _win_total) * 100, 1) - if _win_total > 0 - else None, - "power_draw_w": None, - "power_limit_w": None, - "power_utilization_pct": None, - } - # Linux: DRM sysfs gives system-wide VRAM across all processes, no tools needed. + return _gpu_utilization_payload( + device, + [ + { + "available": True, + "backend": _backend_label(device), + "index": 0, + "visible_ordinal": 0, + "gpu_utilization_pct": _win_util, + "temperature_c": None, + "vram_used_gb": _win_used, + "vram_total_gb": _win_total, + "vram_utilization_pct": round((_win_used / _win_total) * 100, 1) + if _win_total > 0 + else None, + "power_draw_w": None, + "power_limit_w": None, + "power_utilization_pct": None, + } + ], + ) + + # Fallback Linux ROCm if IS_ROCM and platform.system() == "Linux": _linux_used, _linux_total = _rocm_linux_sysfs_vram_gb() if _linux_used is not None and _linux_total is not None: _linux_util = _rocm_linux_sysfs_gpu_busy_pct() _linux_temp = _rocm_linux_sysfs_temp_c() _linux_power = _rocm_linux_sysfs_power_w() - return { - "available": True, - "backend": _backend_label(device), - "gpu_utilization_pct": _linux_util, - "temperature_c": _linux_temp, - "vram_used_gb": _linux_used, - "vram_total_gb": _linux_total, - "vram_utilization_pct": round((_linux_used / _linux_total) * 100, 1) - if _linux_total > 0 - else None, - "power_draw_w": _linux_power, - "power_limit_w": None, - "power_utilization_pct": None, - } - # Last resort: torch mem_get_info (process-local). - _visible_spec = _get_parent_visible_gpu_spec() - _numeric_ids = _visible_spec.get("numeric_ids") or [0] - _primary_idx = [_numeric_ids[0]] if _numeric_ids else [0] - _torch_devices = _torch_get_per_device_info(_primary_idx) - if _torch_devices: - _td = _torch_devices[0] - _total = _td["total_gb"] - _used = _td["used_gb"] - return { - "available": True, - "backend": _backend_label(device), - "gpu_utilization_pct": None, - "temperature_c": None, - "vram_used_gb": _used, - "vram_total_gb": _total, - "vram_utilization_pct": round((_used / _total) * 100, 1) if _total > 0 else None, - "power_draw_w": None, - "power_limit_w": None, - "power_utilization_pct": None, - } + return _gpu_utilization_payload( + device, + [ + { + "available": True, + "backend": _backend_label(device), + "index": 0, + "visible_ordinal": 0, + "gpu_utilization_pct": _linux_util, + "temperature_c": _linux_temp, + "vram_used_gb": _linux_used, + "vram_total_gb": _linux_total, + "vram_utilization_pct": round((_linux_used / _linux_total) * 100, 1) + if _linux_total > 0 + else None, + "power_draw_w": _linux_power, + "power_limit_w": None, + "power_utilization_pct": None, + } + ], + ) - # MLX: _read_apple_gpu_stats() carries both VRAM-used and GPU util%. + # Last resort: torch mem_get_info (process-local) for all visible GPUs + _visible_spec = _get_parent_visible_gpu_spec() + _numeric_ids = _visible_spec.get("numeric_ids") or [] + if not _numeric_ids: + visible_count = _torch_get_physical_gpu_count() or 0 + _numeric_ids = list(range(visible_count)) + + _torch_devices = _torch_get_per_device_info(_numeric_ids) + if _torch_devices: + gpu_array = [] + for _td in _torch_devices: + _total = _td["total_gb"] + _used = _td["used_gb"] + gpu_array.append( + { + "available": True, + "backend": _backend_label(device), + "index": _td["index"], + "name": _td.get("name", "Unknown"), + "gpu_utilization_pct": None, + "temperature_c": None, + "vram_used_gb": _used, + "vram_total_gb": _total, + "vram_utilization_pct": round((_used / _total) * 100, 1) + if _total > 0 + else None, + "power_draw_w": None, + "power_limit_w": None, + "power_utilization_pct": None, + } + ) + return _gpu_utilization_payload(device, gpu_array) + + # MLX if device == DeviceType.MLX: try: import psutil @@ -793,9 +870,8 @@ def get_gpu_utilization() -> Dict[str, Any]: total_bytes = psutil.virtual_memory().total except Exception as e: logger.error(f"Error getting MLX GPU utilization: {e}") - return {"available": False, "backend": device.value, "error": str(e)} - if not agx: - return {"available": False, "backend": device.value} + return {"available": False, "backend": device.value, "devices": [], "error": str(e)} + allocated_bytes = agx.get("vram_used_bytes", 0) or 0 vram_used_gb = allocated_bytes / (1024**3) total_gb = total_bytes / (1024**3) @@ -814,37 +890,51 @@ def get_gpu_utilization() -> Dict[str, Any]: from . import apple - return { - "available": True, - "backend": device.value, - "gpu_utilization_pct": agx.get("utilization_pct") if agx else None, - "temperature_c": apple.read_gpu_temperature_c(), - "vram_used_gb": round(vram_used_gb, 2), - "vram_total_gb": round(total_gb, 2), - "vram_utilization_pct": ( - round((vram_used_gb / total_gb) * 100, 1) if total_gb > 0 else None - ), - "power_draw_w": apple.read_gpu_power_w(), - "power_limit_w": None, - "power_utilization_pct": None, - } + return _gpu_utilization_payload( + device, + [ + { + "available": True, + "backend": device.value, + "index": 0, + "visible_ordinal": 0, + "gpu_utilization_pct": agx.get("utilization_pct") if agx else None, + "temperature_c": apple.read_gpu_temperature_c(), + "vram_used_gb": round(vram_used_gb, 2), + "vram_total_gb": round(total_gb, 2), + "vram_utilization_pct": round((vram_used_gb / total_gb) * 100, 1) + if total_gb > 0 + else None, + "power_draw_w": apple.read_gpu_power_w(), + "power_limit_w": None, + "power_utilization_pct": None, + } + ], + ) mem = get_gpu_memory_info() if device != DeviceType.CPU and mem.get("available"): - return { - "available": True, - "backend": _backend_label(device), - "gpu_utilization_pct": None, - "temperature_c": None, - "vram_used_gb": round(mem.get("allocated_gb", 0), 2), - "vram_total_gb": round(mem.get("total_gb", 0), 2), - "vram_utilization_pct": round(mem.get("utilization_pct", 0), 1), - "power_draw_w": None, - "power_limit_w": None, - "power_utilization_pct": None, - } + return _gpu_utilization_payload( + device, + [ + { + "available": True, + "backend": _backend_label(device), + "index": mem.get("device", 0), + "visible_ordinal": 0, + "gpu_utilization_pct": None, + "temperature_c": None, + "vram_used_gb": round(mem.get("allocated_gb", 0), 2), + "vram_total_gb": round(mem.get("total_gb", 0), 2), + "vram_utilization_pct": round(mem.get("utilization_pct", 0), 1), + "power_draw_w": None, + "power_limit_w": None, + "power_utilization_pct": None, + } + ], + ) - return {"available": False, "backend": _backend_label(device)} + return {"available": False, "backend": _backend_label(device), "devices": []} def _apply_unified_memory_correction( diff --git a/studio/frontend/src/components/floating-monitor.tsx b/studio/frontend/src/components/floating-monitor.tsx new file mode 100644 index 0000000000..f02da6612e --- /dev/null +++ b/studio/frontend/src/components/floating-monitor.tsx @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import { Button } from "@/components/ui/button"; +import { Progress } from "@/components/ui/progress"; +import { useMonitorOverlayStore } from "@/features/settings/stores/monitor-overlay-store"; +import { useSystemInfo } from "@/hooks/use-system"; +import { useT } from "@/i18n"; +import { cn } from "@/lib/utils"; +import { CpuIcon, GripVerticalIcon, XIcon } from "lucide-react"; +import { motion } from "motion/react"; +import { useRef } from "react"; + +function clampPercent(value: number): number { + return Math.max(0, Math.min(100, value)); +} + +function usageIndicatorClass(percent: number): string { + if (percent >= 90) return "bg-destructive"; + if (percent >= 70) return "bg-amber-500"; + return "bg-primary"; +} + +function usageTextClass(percent: number): string { + if (percent >= 90) return "text-destructive"; + if (percent >= 70) return "text-amber-600 dark:text-amber-400"; + return "text-primary"; +} + +function formatGb(value: number): string { + const digits = value >= 10 ? 1 : 2; + return `${value.toFixed(digits)} GB`; +} + +export function FloatingMonitor() { + const t = useT(); + const { isOpen, setIsOpen } = useMonitorOverlayStore(); + const systemInfo = useSystemInfo({ enabled: isOpen, pollMs: 5000 }); + + const constraintsRef = useRef(null); + + if (!isOpen) return null; + + const ramTotal = systemInfo.memory?.total_gb ?? 0; + const ramAvailable = systemInfo.memory?.available_gb ?? 0; + const ramUsed = Math.max(0, ramTotal - ramAvailable); + const ramPercent = clampPercent(systemInfo.memory?.percent_used ?? 0); + + const devices = systemInfo.gpu?.devices ?? []; + const vramTotal = devices.reduce( + (sum, device) => sum + (device.memory_total_gb ?? 0), + 0, + ); + const vramUsed = devices.reduce( + (sum, device) => sum + (device.vram_used_gb ?? 0), + 0, + ); + const vramPercent = clampPercent( + vramTotal > 0 ? (vramUsed / vramTotal) * 100 : 0, + ); + + const hasGpu = (systemInfo.gpu?.available ?? false) && devices.length > 0; + + return ( +
+ +
+
+ + + {t("settings.resources.liveMonitor.title")} + +
+
+
+ +
+ + +
+
+ + +
+
+ {t("settings.resources.liveMonitor.ram")} + + {Math.round(ramPercent)}% + +
+
+ {formatGb(ramUsed)} / {formatGb(ramTotal)} +
+ +
+ + {hasGpu && ( +
+
+ + {t("settings.resources.liveMonitor.vram")}{" "} + {devices.length > 1 + ? `(${devices.length} GPUs)` + : `(${devices[0].name ?? "GPU"})`} + + + {Math.round(vramPercent)}% + +
+
+ {formatGb(vramUsed)} / {formatGb(vramTotal)} +
+ +
+ )} + + +
+ ); +} diff --git a/studio/frontend/src/features/hub/catalog/models-header.tsx b/studio/frontend/src/features/hub/catalog/models-header.tsx index f5afce5c59..10d5a80e5e 100644 --- a/studio/frontend/src/features/hub/catalog/models-header.tsx +++ b/studio/frontend/src/features/hub/catalog/models-header.tsx @@ -15,6 +15,7 @@ import { PackageIcon, RamMemoryIcon, RemoveCircleIcon, + CpuIcon } from "@hugeicons/core-free-icons"; import type { IconSvgElement } from "@hugeicons/react"; import { HugeiconsIcon } from "@hugeicons/react"; @@ -43,6 +44,7 @@ export function ModelsHeader({ isDataset, gpuLabel, ramLabel, + coreLabel, activeCheckpoint, activeGgufVariant, onTitleClick, @@ -53,6 +55,7 @@ export function ModelsHeader({ isDataset: boolean; gpuLabel: string; ramLabel: string; + coreLabel: string; activeCheckpoint: string | null; activeGgufVariant: string | null; onTitleClick: () => void; @@ -84,7 +87,8 @@ export function ModelsHeader({ value={String(localCount)} /> - + + {activeCheckpoint && (
diff --git a/studio/frontend/src/features/hub/hub-page.tsx b/studio/frontend/src/features/hub/hub-page.tsx index 56aa07335d..c3920e18f6 100644 --- a/studio/frontend/src/features/hub/hub-page.tsx +++ b/studio/frontend/src/features/hub/hub-page.tsx @@ -1085,11 +1085,15 @@ export function ModelsPage() { const { vramInfo, minMemory } = useHubModelVram(selectedModel, gpu); const gpuLabel = gpu.available - ? `${Math.floor(gpu.memoryTotalGb)} GB` + ? `${Math.round(gpu.memoryTotalGb)} GB` : "Unavailable"; const ramLabel = - gpu.systemRamAvailableGb > 0 - ? `${Math.floor(gpu.systemRamAvailableGb)} GB` + gpu.systemRamTotalGb > 0 + ? `${Math.round(gpu.systemRamTotalGb)} GB` + : "Unavailable"; + const coreLabel = + gpu.cpuCore > 0 && gpu.cpuThread > 0 + ? `${gpu.cpuCore}/${gpu.cpuThread}` : "Unavailable"; const openNewChat = useCallback(() => { @@ -1453,6 +1457,7 @@ export function ModelsPage() { isDataset={isDatasetMode} gpuLabel={gpuLabel} ramLabel={ramLabel} + coreLabel={coreLabel} activeCheckpoint={activeCheckpoint} activeGgufVariant={activeGgufVariant} onTitleClick={handleResetToDiscover} diff --git a/studio/frontend/src/features/settings/components/usage-examples.tsx b/studio/frontend/src/features/settings/components/usage-examples.tsx index aef2e7ffe6..d66ca6105d 100644 --- a/studio/frontend/src/features/settings/components/usage-examples.tsx +++ b/studio/frontend/src/features/settings/components/usage-examples.tsx @@ -33,44 +33,58 @@ import { updateOpenAIAutoSwitchSettings, } from "../api/openai-auto-switch"; -// API call type; OS axis applies to curl only (Python is OS-identical). type ExampleType = | "curl" | "python" + | "javascript" | "curlTools" | "pythonTools" + | "javascriptTools" | "curlAdvanced" - | "pythonAdvanced"; + | "pythonAdvanced" + | "javascriptAdvanced"; type Os = "unix" | "windows"; -// plain = bare call; tools = server-side tools; advanced = sampling + thinking + tools. type Variant = "plain" | "tools" | "advanced"; const TYPE_TABS: { id: ExampleType; label: string }[] = [ { id: "curl", label: "curl" }, { id: "python", label: "Python" }, + { id: "javascript", label: "JavaScript" }, { id: "curlTools", label: "curl + tools" }, { id: "pythonTools", label: "Python + tools" }, + { id: "javascriptTools", label: "JavaScript + tools" }, { id: "curlAdvanced", label: "curl + advanced" }, { id: "pythonAdvanced", label: "Python + advanced" }, + { id: "javascriptAdvanced", label: "JavaScript + advanced" }, ]; const TYPE_LABEL_KEY: Partial> = { curlTools: "settings.apiKeys.exampleCurlTools", pythonTools: "settings.apiKeys.examplePythonTools", + javascriptTools: "settings.apiKeys.exampleJavaScriptTools", curlAdvanced: "settings.apiKeys.exampleCurlAdvanced", pythonAdvanced: "settings.apiKeys.examplePythonAdvanced", + javascriptAdvanced: "settings.apiKeys.exampleJavaScriptAdvanced", }; const OS_AWARE: Record = { curl: true, python: false, + javascript: false, curlTools: true, pythonTools: false, + javascriptTools: false, curlAdvanced: true, pythonAdvanced: false, + javascriptAdvanced: false, }; const CURL_TYPES = new Set(["curl", "curlTools", "curlAdvanced"]); +const JAVASCRIPT_TYPES = new Set([ + "javascript", + "javascriptTools", + "javascriptAdvanced", +]); const PROMPT = "Can Unsloth Studio do API calling?"; // Auto-switch demo: a second call naming a different downloaded GGUF so the @@ -82,7 +96,6 @@ const SWITCH_MODEL = "your-other-downloaded-GGUF"; const SWITCH_PROMPT = "Now answer as a different model."; // web_search + python + terminal are the reliable built-in tools. const TOOLS = ["web_search", "python", "terminal"]; -// Sampling/thinking knobs for the "+ advanced" examples. const ADV = { temperature: 0.7, top_p: 0.8, @@ -93,37 +106,18 @@ const ADV = { } as const; const DOC_LINKS = [ - { - label: "Claude Code", - href: "https://unsloth.ai/docs/basics/claude-code", - }, - { - label: "Codex", - href: "https://unsloth.ai/docs/basics/codex", - }, - { - label: "OpenClaw", - href: "https://unsloth.ai/docs/integrations/openclaw", - }, - { - label: "OpenCode", - href: "https://unsloth.ai/docs/integrations/opencode", - }, - { - label: "Hermes Agent", - href: "https://unsloth.ai/docs/integrations/hermes-agent", - }, + { label: "Claude Code", href: "https://unsloth.ai/docs/basics/claude-code" }, + { label: "Codex", href: "https://unsloth.ai/docs/basics/codex" }, + { label: "OpenClaw", href: "https://unsloth.ai/docs/integrations/openclaw" }, + { label: "OpenCode", href: "https://unsloth.ai/docs/integrations/opencode" }, + { label: "Hermes Agent", href: "https://unsloth.ai/docs/integrations/hermes-agent" }, ]; -// JSON-encode; also a valid Python literal, so odd model names never break output. const j = (s: string): string => JSON.stringify(s); -// Embed in a POSIX single-quoted string: close, escaped quote, reopen. const shSingle = (s: string): string => s.replace(/'/g, "'\\''"); -// Embed in a PowerShell single-quoted string: '' is a literal quote. const psSingle = (s: string): string => s.replace(/'/g, "''"); const toolsJson = TOOLS.map(j).join(", "); -// Shared body fields (after model/messages, before stream) per variant. function bodyExtraLines(variant: Variant, indent: string): string[] { const lines: string[] = []; if (variant === "advanced") { @@ -152,7 +146,6 @@ function curlBodyPretty(model: string, variant: Variant): string { return `{\n${lines.join("\n")}\n }`; } -// One-line JSON for the Windows body file (PowerShell mangles inline quotes to curl.exe). function winBody(model: string, variant: Variant): string { const body: Record = { model, @@ -172,7 +165,7 @@ function winBody(model: string, variant: Variant): string { body.enabled_tools = TOOLS; } body.stream = true; - return JSON.stringify(body); + return JSON.stringify(body, null, 2); } // A leading comment (valid in both bash and PowerShell) noting the model field @@ -193,7 +186,6 @@ function curlUnix( -d '${shSingle(curlBodyPretty(model, variant))}'`; } -// Windows PowerShell: curl aliases to Invoke-WebRequest, so use curl.exe + body file. function curlWindows( base: string, key: string, @@ -233,7 +225,6 @@ function pythonSnippet( variant: Variant, autoSwitch: boolean, ): string { - // Standard OpenAI args are named; Unsloth extensions go through extra_body. const named = variant === "advanced" ? ` @@ -258,7 +249,6 @@ function pythonSnippet( ${extra.join("\n")} },` : ""; - // With tools, some chunks are tool-lifecycle events with no choices; guard it. const loop = variant !== "plain" ? `for chunk in response: @@ -281,6 +271,70 @@ response = client.chat.completions.create( ${loop}${autoSwitch ? pythonSwitchDemo() : ""}`; } +function javascriptSnippet( + base: string, + key: string, + model: string, + variant: Variant, + autoSwitch: boolean, +): string { + const options: string[] = []; + if (variant === "advanced") { + options.push(` temperature: ${ADV.temperature},`); + options.push(` top_p: ${ADV.top_p},`); + options.push(` max_tokens: ${ADV.max_tokens},`); + } + + // The JS SDK forwards unknown options into the request body, so these go at the + // top level (the Python SDK needs them under extra_body instead). + if (variant === "advanced") { + options.push(` top_k: ${ADV.top_k},`); + options.push(` min_p: ${ADV.min_p},`); + options.push(` repetition_penalty: ${ADV.repetition_penalty},`); + options.push(` enable_thinking: true,`); + } + if (variant !== "plain") { + options.push(` enable_tools: true,`); + options.push(` enabled_tools: [${toolsJson}],`); + } + + const trailingOptions = options.length ? `\n${options.join("\n")}` : ""; + + return `import OpenAI from "openai"; + +const client = new OpenAI({ + baseURL: ${j(`${base}/v1`)}, + apiKey: ${j(key)}, +}); + +const response = await client.chat.completions.create({ + model: ${j(model)}, + messages: [{ role: "user", content: ${j(PROMPT)} }],${trailingOptions} + stream: true, +}); + +for await (const chunk of response) { + process.stdout.write(chunk.choices?.[0]?.delta?.content || ""); +}${autoSwitch ? javascriptSwitchDemo() : ""}`; +} + +function javascriptSwitchDemo(): string { + return ` + +// "Switch model by request" is on: replace the model below with another GGUF you +// have downloaded and Studio loads it before serving. Unknown names keep serving +// the current model. +const switchResponse = await client.chat.completions.create({ + model: ${j(SWITCH_MODEL)}, + messages: [{ role: "user", content: ${j(SWITCH_PROMPT)} }], + stream: true, +}); + +for await (const chunk of switchResponse) { + process.stdout.write(chunk.choices?.[0]?.delta?.content || ""); +}`; +} + function buildSnippets( base: string, key: string, @@ -292,17 +346,24 @@ function buildSnippets( return { curl: curl(base, key, model, "plain", autoSwitch), python: pythonSnippet(base, key, model, "plain", autoSwitch), + javascript: javascriptSnippet(base, key, model, "plain", autoSwitch), curlTools: curl(base, key, model, "tools", autoSwitch), pythonTools: pythonSnippet(base, key, model, "tools", autoSwitch), + javascriptTools: javascriptSnippet(base, key, model, "tools", autoSwitch), curlAdvanced: curl(base, key, model, "advanced", autoSwitch), pythonAdvanced: pythonSnippet(base, key, model, "advanced", autoSwitch), + javascriptAdvanced: javascriptSnippet( + base, + key, + model, + "advanced", + autoSwitch, + ), }; } const KEY_PLACEHOLDER = "sk-unsloth-YOUR_KEY"; const MODEL_FALLBACK = "unsloth/gemma-4-E4B-it-GGUF:UD-Q5_K_XL"; - -// Default ON: when a tunnel exists, examples should show the public base_url. const USE_TUNNEL_KEY = "unsloth_api_use_tunnel"; function readUseTunnelPref(): boolean { @@ -319,11 +380,10 @@ function writeUseTunnelPref(value: boolean): void { try { window.localStorage.setItem(USE_TUNNEL_KEY, value ? "true" : "false"); } catch { - // Non-fatal: the toggle still applies for this session. + // Non-fatal } } -// Active local checkpoint as repo[:variant]; external/none falls back to a default. function useLoadedModelName(): string { const checkpoint = useChatRuntimeStore((s) => s.params.checkpoint); const ggufVariant = useChatRuntimeStore((s) => s.activeGgufVariant); @@ -338,7 +398,6 @@ function useLoadedModelName(): string { }, [checkpoint, ggufVariant]); } -// shiki highlighting via the app's shared code plugin + themes (same as chat). const SHIKI_THEMES = [unslothLightTheme, unslothDarkTheme] as [ typeof unslothLightTheme, typeof unslothDarkTheme, @@ -352,7 +411,6 @@ function HighlightedCode({ code: string; language: string; }) { - // Fence so Streamdown's shiki plugin highlights it (no markdown inside a fence). const markdown = useMemo( () => `\`\`\`${language}\n${code}\n\`\`\``, [code, language], @@ -390,7 +448,6 @@ export function UsageExamples({ apiKey }: { apiKey?: string | null }) { ); const [savingAutoSwitch, setSavingAutoSwitch] = useState(false); - // Tunnel may start after the first /api/health read; refresh so it surfaces here. useEffect(() => { void fetchDeviceType({ force: true }); }, []); @@ -410,10 +467,7 @@ export function UsageExamples({ apiKey }: { apiKey?: string | null }) { }, []); const model = useLoadedModelName(); - // Real key while revealed (before "Done"); otherwise a placeholder. const key = apiKey || KEY_PLACEHOLDER; - // Toggle on + tunnel up: public tunnel URL. Off: backend direct host:port - // (origin is only a last-resort fallback). const origin = typeof window !== "undefined" ? window.location.origin : ""; const base = useTunnel && cloudflareUrl ? cloudflareUrl : (serverUrl ?? origin); @@ -429,7 +483,9 @@ export function UsageExamples({ apiKey }: { apiKey?: string | null }) { ? os === "windows" ? "powershell" : "bash" - : "python"; + : JAVASCRIPT_TYPES.has(lang) + ? "javascript" + : "python"; const handleCopy = async () => { if (await copyToClipboard(snippets[lang])) { @@ -539,8 +595,6 @@ export function UsageExamples({ apiKey }: { apiKey?: string | null }) { )}
- {/* Always rendered (dimmed when off) so toggling never changes the - row height and shifts the code block below. */} - {/* key on the snippet so Streamdown remounts and re-highlights when - only a substring (e.g. the base URL) changes; its block memo - otherwise keeps the stale render. */} ; case "appearance": return ; + case "resources": + return ; case "chat": return ; case "connections": @@ -100,6 +110,7 @@ export function SettingsDialog() { general: null, profile: null, appearance: null, + resources: null, chat: null, connections: null, "api-keys": null, @@ -115,110 +126,113 @@ export function SettingsDialog() { }, [open, activeTab]); return ( - !o && closeDialog()}> - { - // Restore focus to the element that triggered openDialog(). Radix's - // FocusScope races our rAF-scheduled tab focus and loses the - // previous-focus reference, so restore it by hand. - if (opener && opener.isConnected) { - e.preventDefault(); - opener.focus({ preventScroll: true }); - } - }} - className={cn( - // Cap at 820px but shrink to the viewport so it doesn't clip on - // iPad-portrait widths (640-820px) where fixed `w-[820px]` overflows. - "settings-surface !max-w-[min(820px,calc(100vw-2rem))] h-[560px] w-[min(820px,calc(100vw-2rem))] p-0 overflow-hidden", - // Soft shadow, no outline ring. Pin --radius to the light value so - // corner rounding matches in dark mode. - "shadow-border rounded-xl ring-0 [--radius:1.1rem]", - "max-sm:h-dvh max-sm:w-dvw max-sm:!max-w-none max-sm:rounded-none", - )} - > - - {t("settings.dialog.title")} - - - {t("settings.dialog.description")} - -
- + {tab.badgeKey ? ( + + {t(tab.badgeKey)} + + ) : null} + + ); + })} + + -
- -
- {renderTab(activeTab)} -
-
-
- - +
+ +
+ {renderTab(activeTab)} +
+
+ + + + + ); } diff --git a/studio/frontend/src/features/settings/stores/monitor-overlay-store.ts b/studio/frontend/src/features/settings/stores/monitor-overlay-store.ts new file mode 100644 index 0000000000..1af804a19e --- /dev/null +++ b/studio/frontend/src/features/settings/stores/monitor-overlay-store.ts @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import { create } from "zustand"; +import { persist } from "zustand/middleware"; + +interface MonitorOverlayState { + isOpen: boolean; + isMinimized: boolean; + setIsOpen: (open: boolean) => void; + toggleMinimized: () => void; +} + +export const useMonitorOverlayStore = create()( + persist( + (set) => ({ + isOpen: false, + isMinimized: false, + setIsOpen: (isOpen) => set({ isOpen }), + toggleMinimized: () => set((state) => ({ isMinimized: !state.isMinimized })), + }), + { name: "unsloth_monitor_overlay" } + ) +); \ No newline at end of file diff --git a/studio/frontend/src/features/settings/stores/settings-dialog-store.ts b/studio/frontend/src/features/settings/stores/settings-dialog-store.ts index 7fab580f3c..234e92b3d0 100644 --- a/studio/frontend/src/features/settings/stores/settings-dialog-store.ts +++ b/studio/frontend/src/features/settings/stores/settings-dialog-store.ts @@ -7,6 +7,7 @@ export type SettingsTab = | "general" | "profile" | "appearance" + | "resources" | "chat" | "connections" | "api-keys" @@ -60,6 +61,7 @@ function loadInitialTab(): SettingsTab { "general", "profile", "appearance", + "resources", "chat", "connections", "api-keys", diff --git a/studio/frontend/src/features/settings/tabs/general-tab.tsx b/studio/frontend/src/features/settings/tabs/general-tab.tsx index ce69f3d910..df684b7752 100644 --- a/studio/frontend/src/features/settings/tabs/general-tab.tsx +++ b/studio/frontend/src/features/settings/tabs/general-tab.tsx @@ -104,6 +104,7 @@ const PREFS_KEYS: string[] = [ "tour:studio:v1", // Update notifications "unsloth_show_llama_update_banner", + "unsloth_monitor_overlay", ]; // Set by resetAllPrefs so the unmount-commit effect skips writing back the diff --git a/studio/frontend/src/features/settings/tabs/resources-tab.tsx b/studio/frontend/src/features/settings/tabs/resources-tab.tsx new file mode 100644 index 0000000000..d5e19cc51c --- /dev/null +++ b/studio/frontend/src/features/settings/tabs/resources-tab.tsx @@ -0,0 +1,477 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import { Button } from "@/components/ui/button"; +import { Progress } from "@/components/ui/progress"; +import { Switch } from "@/components/ui/switch"; +import { openModelsDir } from "@/features/native-intents"; +import { useSystemInfo, type GpuDevice } from "@/hooks/use-system"; +import { isTauri } from "@/lib/api-base"; +import { copyToClipboard } from "@/lib/copy-to-clipboard"; +import { toast } from "@/lib/toast"; +import { cn } from "@/lib/utils"; +import { useT } from "@/i18n"; +import { useEffect, useMemo, useState } from "react"; +import { loadModelsFolder, type ModelsFolder } from "../api/models-folder"; +import { SettingsRow } from "../components/settings-row"; +import { SettingsSection } from "../components/settings-section"; +import { useMonitorOverlayStore } from "../stores/monitor-overlay-store"; +import { LayersIcon } from "lucide-react"; + +const POLL_MS = 3000; + +function isFiniteNumber(value: number | null | undefined): value is number { + return typeof value === "number" && Number.isFinite(value); +} + +function clampPercent(value: number | null | undefined): number { + if (!isFiniteNumber(value)) return 0; + return Math.max(0, Math.min(100, value)); +} + +function usageIndicatorClass(percent: number): string { + if (percent >= 90) return "bg-destructive"; + if (percent >= 70) return "bg-amber-500"; + return "bg-primary"; +} + +function usageTextClass(percent: number): string { + if (percent >= 90) return "text-destructive"; + if (percent >= 70) return "text-amber-600 dark:text-amber-400"; + return "text-primary"; +} + +function formatGb(value: number | null | undefined): string { + const safe = isFiniteNumber(value) ? Math.max(0, value) : 0; + const digits = safe >= 10 ? 1 : 2; + return `${safe.toFixed(digits)} GB`; +} + +function formatMb(value: number | null | undefined): string { + const safe = isFiniteNumber(value) ? Math.max(0, value) : 0; + return `${Math.round(safe).toLocaleString()} MB`; +} + +function formatPercent(value: number | null | undefined): string { + return `${Math.round(clampPercent(value))}%`; +} + +function formatFrequency(mhz: number | null | undefined): string | null { + if (!isFiniteNumber(mhz) || mhz <= 0) return null; + if (mhz >= 1000) return `${(mhz / 1000).toFixed(2)} GHz`; + return `${Math.round(mhz)} MHz`; +} + +function formatUptime(seconds: number | null | undefined): string { + if (!isFiniteNumber(seconds) || seconds <= 0) return "0m"; + const minutes = Math.floor(seconds / 60); + const hours = Math.floor(minutes / 60); + const days = Math.floor(hours / 24); + if (days > 0) return `${days}d ${hours % 24}h`; + if (hours > 0) return `${hours}h ${minutes % 60}m`; + return `${Math.max(1, minutes)}m`; +} + +function MetricTile({ + label, + value, + detail, + percent, +}: { + label: string; + value: string; + detail: string; + percent: number; +}) { + const safePercent = clampPercent(percent); + return ( +
+
+ + {label} + + + {formatPercent(safePercent)} + +
+
+
+ {value} +
+
+ {detail} +
+
+ +
+ ); +} + +function InfoRow({ + label, + value, + detail, +}: { + label: string; + value: string; + detail?: string; +}) { + return ( +
+ + {label} + + + {detail ? `${value} (${detail})` : value} + +
+ ); +} + +function deviceOrdinal(device: GpuDevice): number | undefined { + return device.visible_ordinal ?? device.index; +} + +export function ResourcesTab() { + const t = useT(); + const [liveUpdates, setLiveUpdates] = useState(true); + const { isOpen, setIsOpen } = useMonitorOverlayStore(); + const systemInfo = useSystemInfo({ + enabled: liveUpdates, + pollMs: liveUpdates ? POLL_MS : undefined, + }); + const [modelsFolder, setModelsFolder] = useState(null); + const [modelsFolderLoaded, setModelsFolderLoaded] = useState(false); + + useEffect(() => { + let cancelled = false; + void loadModelsFolder() + .then((folder) => { + if (cancelled) return; + setModelsFolder(folder); + setModelsFolderLoaded(true); + }) + .catch(() => { + if (cancelled) return; + setModelsFolderLoaded(true); + }); + return () => { + cancelled = true; + }; + }, []); + + const metrics = useMemo(() => { + const devices = systemInfo.gpu?.devices ?? []; + const ramTotal = systemInfo.memory?.total_gb ?? 0; + const ramAvailable = systemInfo.memory?.available_gb ?? 0; + const ramUsed = Math.max(0, ramTotal - ramAvailable); + const diskTotal = systemInfo.disk?.total_gb ?? 0; + const diskFree = systemInfo.disk?.free_gb ?? 0; + const diskUsed = Math.max(0, diskTotal - diskFree); + const vramTotal = devices.reduce( + (sum, device) => sum + (device.memory_total_gb ?? 0), + 0, + ); + const vramUsed = devices.reduce( + (sum, device) => sum + (device.vram_used_gb ?? 0), + 0, + ); + const vramFree = devices.reduce( + (sum, device) => + sum + + (device.vram_free_gb ?? + Math.max(0, (device.memory_total_gb ?? 0) - (device.vram_used_gb ?? 0))), + 0, + ); + const vramPercent = vramTotal > 0 ? (vramUsed / vramTotal) * 100 : 0; + + return { + devices, + ramTotal, + ramUsed, + diskTotal, + diskFree, + diskUsed, + vramTotal, + vramUsed, + vramFree, + vramPercent, + }; + }, [systemInfo]); + + const handleModelsFolder = async () => { + const folder = modelsFolder; + if (!folder) return; + if (isTauri) { + try { + await openModelsDir(folder.path); + } catch (error) { + toast.error(t("settings.resources.storage.openError"), { + description: error instanceof Error ? error.message : undefined, + }); + } + return; + } + if (await copyToClipboard(folder.path)) { + toast.success(t("settings.resources.storage.copied")); + } else { + toast.error(t("settings.resources.storage.copyError")); + } + }; + + const cpuCoresLabel = + systemInfo.cpu?.logical_count && systemInfo.cpu?.physical_count + ? t("settings.resources.liveMonitor.cpuCores", { + logical: systemInfo.cpu.logical_count, + physical: systemInfo.cpu.physical_count, + }) + : t("settings.resources.environment.unknown"); + const cpuFrequencyLabel = formatFrequency(systemInfo.cpu?.frequency_mhz); + const hasGpu = + (systemInfo.gpu?.available ?? false) && metrics.devices.length > 0; + const backendLabel = ( + systemInfo.gpu?.backend ?? systemInfo.device_backend ?? "cpu" + ).toUpperCase(); + const modelsFolderPath = modelsFolder + ? modelsFolder.path + : modelsFolderLoaded + ? t("settings.resources.environment.unknown") + : t("common.loading"); + + return ( +
+
+
+

+ {t("settings.resources.title")} +

+

+ {t("settings.resources.description")} +

+
+
+ + +
+ {t("settings.resources.liveUpdates")} + +
+
+
+ + +
+ + + + +
+ + + + {hasGpu ? ( + metrics.devices.map((device, index) => { + const ordinal = deviceOrdinal(device); + const total = device.memory_total_gb ?? 0; + const used = device.vram_used_gb ?? 0; + const free = device.vram_free_gb ?? Math.max(0, total - used); + const percent = + device.vram_utilization_pct ?? + (total > 0 ? (used / total) * 100 : null); + const safePercent = clampPercent(percent); + return ( +
+
+
+
+ {device.name ?? + t("settings.resources.gpu.unknownDevice")} +
+
+ {ordinal === undefined + ? backendLabel + : `${t("settings.resources.gpu.deviceWithIndex", { + index: ordinal, + })}, ${backendLabel}`} +
+
+
+ + {formatPercent(safePercent)}{" "} + {t("settings.resources.gpu.vramUtilization")} + +
+
+
+ + {t("settings.resources.gpu.used", { + value: formatGb(used), + })} + + + {t("settings.resources.gpu.free", { + value: formatGb(free), + })} + + + {t("settings.resources.gpu.total", { + value: formatGb(total), + })} + +
+ +
+ ); + }) + ) : ( +
+ {t("settings.resources.gpu.noGpu")} +
+ )} + + + + + +
+ + {modelsFolderPath} + + +
+ + + + + + + + + + + +
+ ); +} diff --git a/studio/frontend/src/features/studio/sections/progress-section.tsx b/studio/frontend/src/features/studio/sections/progress-section.tsx index 6aaca86e0b..abab35db93 100644 --- a/studio/frontend/src/features/studio/sections/progress-section.tsx +++ b/studio/frontend/src/features/studio/sections/progress-section.tsx @@ -29,6 +29,7 @@ import { import { getTrainingMethodLabel } from "@/features/training/lib/training-methods"; import type { TrainingViewData } from "@/features/training"; import { useGpuUtilization } from "@/hooks"; +import type { GpuUtilization } from "@/hooks/use-gpu-utilization"; import { cn } from "@/lib/utils"; import { ChartAverageIcon, @@ -42,7 +43,7 @@ import { } from "@hugeicons/core-free-icons"; import { HugeiconsIcon } from "@hugeicons/react"; import { Link, useNavigate } from "@tanstack/react-router"; -import { type ReactElement, type ReactNode, useState } from "react"; +import { type ReactElement, type ReactNode, useEffect, useState } from "react"; import { useShallow } from "zustand/react/shallow"; import { ChartSettingsSheet } from "./charts/chart-settings-sheet"; import { @@ -123,18 +124,17 @@ export function ProgressSection({ const [stopDialogOpen, setStopDialogOpen] = useState(false); const [stopRequestedLocal, setStopRequestedLocal] = useState(false); - // Auto-resets when training stops; no useEffect needed const stopRequested = data.isTrainingRunning && stopRequestedLocal; const pct = data.totalSteps > 0 ? Math.min( - 100, - Math.max( - 0, - Math.round((data.currentStep / data.totalSteps) * 100), - ), - ) + 100, + Math.max( + 0, + Math.round((data.currentStep / data.totalSteps) * 100), + ), + ) : Math.round(data.progressPercent); const elapsed = data.elapsedSeconds; @@ -214,16 +214,16 @@ export function ProgressSection({ }, ...(data.trainingMethod !== "full" ? [ - { - section: "LoRA", - rows: [ - configRow(t("studio.progress.rank"), cfgLoraRank), - configRow(t("studio.progress.alpha"), cfgLoraAlpha), - configRow(t("studio.progress.dropout"), cfgLoraDropout), - configRow(t("studio.progress.variant"), cfgLoraVariant), - ], - }, - ] + { + section: "LoRA", + rows: [ + configRow(t("studio.progress.rank"), cfgLoraRank), + configRow(t("studio.progress.alpha"), cfgLoraAlpha), + configRow(t("studio.progress.dropout"), cfgLoraDropout), + configRow(t("studio.progress.variant"), cfgLoraVariant), + ], + }, + ] : []), ]; @@ -350,8 +350,8 @@ export function ProgressSection({ {stepsPerSecond == null ? t("studio.progress.noStepsPerSecond") : t("studio.progress.stepsPerSecond", { - value: stepsPerSecond.toFixed(2), - })} + value: stepsPerSecond.toFixed(2), + })} {data.currentNumTokens != null && ( {t("studio.progress.tokens", { value: data.currentNumTokens })} @@ -373,14 +373,50 @@ function LiveGpuPanel({ isTrainingRunning: boolean; }): ReactElement { const t = useT(); - const gpu = useGpuUtilization(isTrainingRunning); + const [selectedGpu, setSelectedGpu] = useState(0); + const gpuData = useGpuUtilization(isTrainingRunning); + const gpus: GpuUtilization[] = + Array.isArray(gpuData?.devices) && gpuData.devices.length > 0 + ? gpuData.devices + : gpuData && Object.keys(gpuData).length > 0 + ? [gpuData] + : []; + + useEffect(() => { + if (selectedGpu > 0 && selectedGpu >= gpus.length) { + setSelectedGpu(0); + } + }, [gpus.length, selectedGpu]); + + const gpuCount = gpus.length; + const currentGpu: Partial = gpus[selectedGpu] || gpus[0] || {}; return (
-
-

- {t("studio.progress.gpuMonitor")} -

+
+
+

+ {t("studio.progress.gpuMonitor")} +

+ {gpuCount > 1 && ( + + )} +
{t("studio.progress.live")} @@ -388,51 +424,44 @@ function LiveGpuPanel({
- } + icon={} value={ - gpu.gpu_utilization_pct != null - ? `${gpu.gpu_utilization_pct}%` + currentGpu.gpu_utilization_pct != null + ? `${currentGpu.gpu_utilization_pct}%` : "--" } - pct={gpu.gpu_utilization_pct ?? 0} + pct={currentGpu.gpu_utilization_pct ?? 0} /> - } + icon={} value={ - gpu.temperature_c != null ? `${gpu.temperature_c}°C` : "--" + currentGpu.temperature_c != null ? `${currentGpu.temperature_c}°C` : "--" } - pct={gpu.temperature_c ?? 0} + pct={currentGpu.temperature_c ?? 0} max={100} /> } value={ - gpu.vram_used_gb != null && gpu.vram_total_gb != null - ? `${gpu.vram_used_gb} / ${gpu.vram_total_gb} GB` + currentGpu.vram_used_gb != null && currentGpu.vram_total_gb != null + ? `${currentGpu.vram_used_gb} / ${currentGpu.vram_total_gb} GB` : "--" } - pct={gpu.vram_utilization_pct ?? 0} + pct={currentGpu.vram_utilization_pct ?? 0} /> } value={ - gpu.power_draw_w != null - ? gpu.power_limit_w != null - ? `${gpu.power_draw_w} / ${gpu.power_limit_w} W` - : `${gpu.power_draw_w} W` + currentGpu.power_draw_w != null + ? currentGpu.power_limit_w != null + ? `${currentGpu.power_draw_w} / ${currentGpu.power_limit_w} W` + : `${currentGpu.power_draw_w} W` : "--" } - pct={gpu.power_utilization_pct ?? 0} + pct={currentGpu.power_utilization_pct ?? 0} />
@@ -560,7 +589,10 @@ function TrainingHeaderActions({ {stopRequested ? t("studio.training.stopping") : t("studio.training.stopAction")} - + {t("studio.training.stopTitle")} diff --git a/studio/frontend/src/hooks/index.ts b/studio/frontend/src/hooks/index.ts index d5c923d57d..5b2fa43ae7 100644 --- a/studio/frontend/src/hooks/index.ts +++ b/studio/frontend/src/hooks/index.ts @@ -1,6 +1,7 @@ // SPDX-License-Identifier: AGPL-3.0-only // Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + export { useDebouncedValue } from "./use-debounced-value"; export { useGpuInfo } from "./use-gpu-info"; export { useGpuUtilization } from "./use-gpu-utilization"; @@ -9,3 +10,4 @@ export { useHfDatasetSplits } from "./use-hf-dataset-splits"; export { useHfTokenValidation } from "./use-hf-token-validation"; export { useTauriBackend } from "./use-tauri-backend"; export { useCollapseScrollLock } from "./use-collapse-scroll-lock"; +export { useSystemInfo } from "./use-system"; diff --git a/studio/frontend/src/hooks/use-gpu-info.ts b/studio/frontend/src/hooks/use-gpu-info.ts index eb4d89abd8..1e313acdf3 100644 --- a/studio/frontend/src/hooks/use-gpu-info.ts +++ b/studio/frontend/src/hooks/use-gpu-info.ts @@ -3,19 +3,26 @@ import { authFetch } from "@/features/auth"; import { useEffect, useState } from "react"; +import type { SystemInfoResponse } from "./use-system"; export interface GpuInfo { available: boolean; name: string; memoryTotalGb: number; + cpuCore: number; + cpuThread: number; systemRamAvailableGb: number; + systemRamTotalGb: number } const DEFAULT_GPU: GpuInfo = { available: false, name: "Unknown", memoryTotalGb: 0, + cpuCore: 0, + cpuThread: 0, systemRamAvailableGb: 0, + systemRamTotalGb: 0 }; // Module-level cache so multiple components share one fetch. @@ -30,24 +37,30 @@ async function fetchGpuOnce(): Promise { try { const res = await authFetch("/api/system"); if (!res.ok) throw new Error(`HTTP ${res.status}`); - const data = await res.json(); - const ramAvailableGb = data?.memory?.available_gb ?? 0; + + const data = await res.json() as SystemInfoResponse; const gpuData = data?.gpu; - if (!gpuData?.available || !gpuData.devices?.length) { - // No discrete GPU (e.g. Mac): still surface system RAM so memory math - // (unified memory) has a budget to work with. - const info: GpuInfo = { ...DEFAULT_GPU, systemRamAvailableGb: ramAvailableGb }; - cachedGpu = info; - return info; - } - const devices = gpuData.devices as Array<{ name?: string; memory_total_gb?: number }>; - const totalGb = devices.reduce((sum, d) => sum + (d.memory_total_gb ?? 0), 0); - const info: GpuInfo = { - available: true, - name: devices[0]?.name ?? "Unknown", - memoryTotalGb: totalGb, - systemRamAvailableGb: ramAvailableGb, + + // CPU/RAM exist even on hosts without a GPU, so populate them on every path. + // No discrete GPU (e.g. Mac): still surface system RAM so memory math + // (unified memory) has a budget to work with. + const base = { + cpuCore: data?.cpu?.physical_count ?? 0, + cpuThread: data?.cpu?.logical_count ?? 0, + systemRamAvailableGb: data?.memory?.available_gb ?? 0, + systemRamTotalGb: data?.memory?.total_gb ?? 0, }; + + const devices = gpuData?.devices ?? []; + const info: GpuInfo = + gpuData?.available && devices.length + ? { + ...base, + available: true, + name: devices[0]?.name ?? "Unknown", + memoryTotalGb: devices.reduce((sum, d) => sum + (d.memory_total_gb ?? 0), 0), + } + : { ...DEFAULT_GPU, ...base }; cachedGpu = info; return info; } catch { @@ -78,4 +91,4 @@ export function useGpuInfo(): GpuInfo { }, []); return gpu; -} +} \ No newline at end of file diff --git a/studio/frontend/src/hooks/use-gpu-utilization.ts b/studio/frontend/src/hooks/use-gpu-utilization.ts index 1a9f6102dd..be16647a4d 100644 --- a/studio/frontend/src/hooks/use-gpu-utilization.ts +++ b/studio/frontend/src/hooks/use-gpu-utilization.ts @@ -7,6 +7,9 @@ import { useEffect, useRef, useState } from "react"; export interface GpuUtilization { available: boolean; backend: string | null; + devices?: GpuUtilization[]; + index?: number; + visible_ordinal?: number; gpu_utilization_pct: number | null; temperature_c: number | null; vram_used_gb: number | null; @@ -57,11 +60,10 @@ export function useGpuUtilization( const json = (await res.json()) as GpuUtilization; if (!cancelled) setData(json); } catch { - // Silently ignore — next poll will retry + // Retry on the next poll. } } - // Fetch immediately, then set up interval void poll(); timerRef.current = setInterval(() => void poll(), intervalMs); diff --git a/studio/frontend/src/hooks/use-system.ts b/studio/frontend/src/hooks/use-system.ts new file mode 100644 index 0000000000..a135cce86e --- /dev/null +++ b/studio/frontend/src/hooks/use-system.ts @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import { authFetch } from "@/features/auth"; +import { useEffect, useState } from "react"; + +export interface GpuDevice { + index?: number; + index_kind?: string; + visible_ordinal?: number; + name?: string; + memory_total_gb?: number; + vram_used_gb?: number; + vram_free_gb?: number; + vram_utilization_pct?: number | null; +} + +export interface SystemInfoResponse { + platform: string; + python_version: string; + device_backend: "cuda" | "rocm" | "cpu" | "mlx" | "xpu"; + uptime_seconds: number | null; + cpu: { + logical_count: number; + physical_count: number; + usage_percent: number; + frequency_mhz: number | null; + }; + memory: { + total_gb: number; + available_gb: number; + percent_used: number; + process_used_mb: number; + }; + disk: { + total_gb: number; + free_gb: number; + percent_used: number; + }; + gpu: { + available: boolean; + backend?: string; + backend_cuda_visible_devices?: string | null; + parent_visible_gpu_ids?: number[]; + index_kind?: string; + devices: GpuDevice[]; + }; + ml_packages: { + torch?: string; + transformers?: string; + }; +} + +let cachedSystem: SystemInfoResponse | null = null; +let systemFetchPromise: Promise | null = null; + +const DEFAULT_SYSTEM: SystemInfoResponse = { + platform: "Unknown", + python_version: "Unknown", + device_backend: "cpu", + uptime_seconds: 0, + cpu: { logical_count: 0, physical_count: 0, usage_percent: 0, frequency_mhz: null }, + memory: { total_gb: 0, available_gb: 0, percent_used: 0, process_used_mb: 0 }, + disk: { total_gb: 0, free_gb: 0, percent_used: 0 }, + gpu: { available: false, devices: [] }, + ml_packages: {} +}; + +async function fetchSystemOnce({ + force = false, +}: { force?: boolean } = {}): Promise { + if (systemFetchPromise) return systemFetchPromise; + if (!force && cachedSystem) return cachedSystem; + + systemFetchPromise = (async () => { + try { + const res = await authFetch("/api/system"); + if (!res.ok) throw new Error(`HTTP ${res.status}`); + const data = await res.json(); + + cachedSystem = data as SystemInfoResponse; + return cachedSystem; + } catch { + cachedSystem = null; + return DEFAULT_SYSTEM; + } finally { + systemFetchPromise = null; + } + })(); + + return systemFetchPromise; +} + +interface UseSystemInfoOptions { + pollMs?: number; + enabled?: boolean; +} + +export function useSystemInfo({ + pollMs, + enabled = true, +}: UseSystemInfoOptions = {}): SystemInfoResponse { + const [systemInfo, setSystemInfo] = useState(cachedSystem ?? DEFAULT_SYSTEM); + + useEffect(() => { + if (!enabled) return; + + let cancelled = false; + let timeoutId: number | null = null; + + const update = (force: boolean) => { + void fetchSystemOnce({ force }) + .then((info) => { + if (!cancelled) setSystemInfo(info); + }) + .finally(() => { + if (cancelled || !pollMs) return; + timeoutId = window.setTimeout(() => update(true), pollMs); + }); + }; + + update(Boolean(pollMs)); + return () => { + cancelled = true; + if (timeoutId !== null) window.clearTimeout(timeoutId); + }; + }, [enabled, pollMs]); + + return systemInfo; +} diff --git a/studio/frontend/src/i18n/AGENTS.md b/studio/frontend/src/i18n/AGENTS.md index 42d964acca..35c025cd0b 100644 --- a/studio/frontend/src/i18n/AGENTS.md +++ b/studio/frontend/src/i18n/AGENTS.md @@ -2,10 +2,11 @@ - `locales/en.ts` is the complete baseline message file. - Non-English locale files may be partial. Missing keys must fall back to English at runtime. -- Use BCP 47 locale tags for new languages, for example `zh-CN`, `ja-JP`, and `ko-KR`. +- Use BCP 47 locale tags for new languages, for example `zh-CN`, `pt-BR`, `ja-JP`, and `ko-KR`. - Do not change fallback logic to hide missing translations. - Do not add automatic DOM translation, MutationObserver text replacement, or runtime guess-based translation. - Preserve interpolation variables exactly, for example `{count}`, `{model}`, and `{provider}`. - Keep product and technical names unchanged unless there is an established localized name, for example `Unsloth Studio`, `LoRA`, `GGUF`, and `Hugging Face`. - Keep translation changes small and reviewable. Prefer separate commits for runtime changes, UI migration, and locale text. - When adding user-facing Studio UI text, add the English message key first and add non-English overrides only when the translation is clear. +- Run `npx tsx src/i18n/check-parity.ts` before committing to ensure there are no shape mismatches or placeholder discrepancies in the non-English overlays. \ No newline at end of file diff --git a/studio/frontend/src/i18n/check-parity.ts b/studio/frontend/src/i18n/check-parity.ts index 8c027f9ce3..e2b66f5cdc 100644 --- a/studio/frontend/src/i18n/check-parity.ts +++ b/studio/frontend/src/i18n/check-parity.ts @@ -3,13 +3,14 @@ // Parity check between en.ts and every non-English locale. // - Locale files may be partial; missing keys must fall back to English. -// - All zh-CN keys must exist in en (no extras). +// - All non-English keys must exist in en (no extras). // - Placeholder set must match per leaf between en and the overlay. // // Run: npx tsx src/i18n/check-parity.ts import { en } from "./locales/en.ts"; import { zhCN } from "./locales/zh-CN.ts"; +import { ptBR } from "./locales/pt-br.ts"; import { ja } from "./locales/ja.ts"; type Tree = { readonly [k: string]: string | Tree }; @@ -90,6 +91,7 @@ function checkExtras( const overlays: Record = { "zh-CN": zhCN as unknown as Tree, + "pt-BR": ptBR as unknown as Tree, "ja": ja as unknown as Tree, }; let anyError = false; @@ -112,4 +114,4 @@ for (const [locale, overlay] of Object.entries(overlays)) { } if (anyError) process.exit(1); -console.log("\nAll locale overlays pass parity."); +console.log("\nAll locale overlays pass parity."); \ No newline at end of file diff --git a/studio/frontend/src/i18n/locales/en.ts b/studio/frontend/src/i18n/locales/en.ts index 136e8523ba..92abc222a0 100644 --- a/studio/frontend/src/i18n/locales/en.ts +++ b/studio/frontend/src/i18n/locales/en.ts @@ -92,6 +92,7 @@ export const en = { general: "General", profile: "Profile", appearance: "Appearance", + resources: "System", chat: "Chat", connections: "Connections", apiKeys: "API", @@ -275,6 +276,58 @@ export const en = { "Keep the sidebar expanded instead of collapsing to icons.", }, }, + resources: { + title: "System", + description: "Monitor this Studio server's hardware and storage.", + liveUpdates: "Live updates", + floatingWindow: "Floating window", + disableOverlay: "Disable overlay", + liveMonitor: { + title: "Live monitor", + cpu: "CPU", + ram: "RAM", + disk: "Disk", + vram: "VRAM", + cpuCores: "{logical} logical / {physical} physical cores", + currentLoad: "Current load", + free: "{value} free", + noGpu: "No visible GPU", + }, + gpu: { + title: "GPU devices", + noGpu: "No visible GPU detected. CPU-only resources are shown above.", + unknownDevice: "Unknown GPU", + deviceWithIndex: "GPU {index}", + vramUtilization: "VRAM", + used: "{value} used", + free: "{value} free", + total: "{value} total", + }, + storage: { + title: "Storage", + systemDisk: "System disk", + diskUsage: "{used} used / {total}", + diskFree: "{free} free", + modelsFolder: "Models folder", + modelsFolderDescription: "Where downloaded models are stored.", + openAction: "Open", + copyAction: "Copy path", + copied: "Path copied", + openError: "Couldn't open the folder", + copyError: "Couldn't copy the path", + }, + environment: { + title: "Environment", + backend: "Backend", + python: "Python", + torch: "Torch", + transformers: "Transformers", + uptime: "Uptime", + processMemory: "Process memory", + notInstalled: "Not installed", + unknown: "Unknown", + }, + }, chat: { title: "Chat", description: "Manage chat history stored on this device.", @@ -373,8 +426,10 @@ export const en = { usageTools: "Tools", exampleCurlTools: "curl + tools", examplePythonTools: "Python + tools", + exampleJavaScriptTools: "JavaScript + tools", exampleCurlAdvanced: "curl + advanced", examplePythonAdvanced: "Python + advanced", + exampleJavaScriptAdvanced: "JavaScript + advanced", osUnix: "Linux / macOS / WSL", osWindows: "Windows", secureHttps: "Secure HTTPS", diff --git a/studio/frontend/src/i18n/locales/pt-br.ts b/studio/frontend/src/i18n/locales/pt-br.ts new file mode 100644 index 0000000000..c261e4ed0c --- /dev/null +++ b/studio/frontend/src/i18n/locales/pt-br.ts @@ -0,0 +1,934 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +export const ptBR = { + common: { + cancel: "Cancelar", + close: "Fechar", + delete: "Excluir", + done: "Concluído", + error: "Erro", + export: "Exportar", + help: "Ajuda", + loading: "Carregando...", + new: "Novo", + rename: "Renomear", + save: "Salvar", + saving: "Salvando...", + search: "Buscar", + shutdown: "Desligar", + }, + shell: { + beta: "BETA", + brand: "unsloth", + product: "Unsloth Studio", + accountMenu: "Menu de conta {name}", + updateAvailable: "Atualização disponível", + aria: { + home: "Início do Unsloth", + closeSidebar: "Fechar barra lateral", + openSidebar: "Abrir barra lateral", + chatOptions: "Opções de chat", + runOptions: "Opções de execução", + }, + navigation: { + newChat: "Novo Chat", + returnToChat: "Retornar ao Chat", + compare: "Comparar", + search: "Buscar", + hub: "Hub", + train: "Treinar", + recipes: "Receitas", + export: "Exportar", + recents: "Recentes", + settings: "Configurações", + api: "API", + lightMode: "Modo Claro", + darkMode: "Modo Escuro", + guidedTour: "Tour Guiado", + help: "Ajuda", + logOut: "Sair", + shutdown: "Desligar", + }, + notFound: { + title: "Página não encontrada", + description: "{path} não existe.", + backToChat: "Voltar para o chat", + }, + dialog: { + deleteChat: { + title: "Excluir chat", + description: 'Tem certeza de que deseja excluir este chat "{name}"?', + }, + deleteRun: { + title: "Excluir execução de treino", + description: 'Tem certeza de que deseja excluir esta execução "{name}"?', + }, + renameChat: { + title: "Renomear chat", + placeholder: "Título do chat", + }, + renameRun: { + title: "Renomear execução", + placeholder: "Nome da execução", + }, + }, + toast: { + cannotDeleteRunningRun: "Não é possível excluir uma execução de treino em andamento", + failedToDeleteChat: "Falha ao excluir o chat", + failedToDeleteRun: "Falha ao excluir a execução", + failedToRenameChat: "Falha ao renomear o chat", + failedToRenameRun: "Falha ao renomear a execução", + }, + }, + settings: { + title: "Configurações", + dialog: { + title: "Configurações", + description: "Gerencie suas preferências do Unsloth.", + closeAriaLabel: "Fechar configurações", + }, + tabs: { + general: "Geral", + profile: "Perfil", + appearance: "Aparência", + resources: "Sistema", + chat: "Chat", + connections: "Conexões", + apiKeys: "API", + about: "Sobre", + }, + general: { + title: "Geral", + description: "Preferências globais do Unsloth.", + account: "Conta", + huggingFaceToken: "Token do Hugging Face", + huggingFaceTokenDescription: + "Usado para carregar modelos restritos e enviar artefatos.", + tokenSaved: "Token salvo", + hideToken: "Ocultar token", + showToken: "Mostrar token", + password: "Senha", + passwordDescription: "Altere a senha desta conta do Studio.", + passwordDialog: { + trigger: "Alterar senha", + title: "Alterar senha", + description: + "Insira sua senha atual e escolha uma nova (no mínimo {minLength} caracteres).", + currentPassword: "Senha atual", + newPassword: "Nova senha", + confirmPassword: "Confirmar nova senha", + currentTooShort: + "A senha atual deve ter no mínimo {minLength} caracteres.", + newTooShort: "A nova senha deve ter no mínimo {minLength} caracteres.", + mismatch: "As senhas não coincidem.", + samePassword: + "A nova senha deve ser diferente da senha atual.", + update: "Atualizar senha", + updating: "Atualizando...", + updated: "Senha atualizada.", + updateFailed: "Falha ao atualizar a senha.", + }, + chatDefaults: "Padrões do chat", + autoTitleNewChats: "Gerar título automático para novos chats", + autoTitleNewChatsDescription: + "Gera um título curto a partir da primeira mensagem.", + helperLlm: { + sectionTitle: "LLM Auxiliar", + preloadOnStartup: "Pré-carregar LLM Auxiliar na inicialização", + preloadOnStartupDescription: + "Baixa o modelo auxiliar do Assistente de IA em segundo plano ao iniciar. Desativado por padrão; o Assistente de IA ainda pode buscá-lo sob demanda.", + disabledByEnv: + "Desativado por UNSLOTH_HELPER_MODEL_DISABLE no ambiente de backend.", + loadError: "Falha ao carregar as configurações do LLM Auxiliar.", + saveError: "Falha ao salvar as configurações do LLM Auxiliar.", + }, + notifications: { + sectionTitle: "Notificações", + showLlamaUpdates: "Notificações de atualização do llama.cpp", + showLlamaUpdatesDescription: + "Notifica quando uma nova versão do llama.cpp estiver disponível. Desative se você apenas realiza treinos.", + }, + gettingStarted: "Primeiros passos", + startOnboarding: "Iniciar integração", + startOnboardingDescription: + "Reabre o assistente de configuração sem alterar sua conta.", + startOnboardingAction: "Iniciar integração", + uploads: { + sectionTitle: "Uploads", + maxUploadSize: "Limite de upload do dataset de treino", + maxUploadSizeDescription: + "O padrão é {defaultSize} MB.", + }, + storage: { + sectionTitle: "Armazenamento", + modelsFolder: "Pasta de modelos", + modelsFolderDescription: + "Onde os modelos baixados são armazenados.", + openAction: "Abrir", + copyAction: "Copiar caminho", + copied: "Caminho copiado", + openError: "Não foi possível abrir a pasta", + copyError: "Não foi possível copiar o caminho", + }, + resetPreferences: { + sectionTitle: "Zona de perigo", + label: "Redefinir todas as preferências locais", + description: + "Limpa apenas as preferências locais. Chats, acesso à API e configurações salvas no banco de dados são mantidos.", + action: "Redefinir preferências", + confirmTitle: "Redefinir todas as preferências locais?", + confirmDescription: + "Limpa as preferências locais e recarrega o Unsloth. Chats, acesso à API e configurações salvas no banco de dados são mantidos.", + confirmAction: "Redefinir e recarregar", + }, + }, + profile: { + title: "Perfil", + description: "Como seu perfil aparece no Unsloth.", + changePicture: "Alterar foto de perfil", + displayName: "Nome de exibição", + nickname: "Como o Unsloth deve chamar você?", + nicknamePlaceholder: "Apelido", + nicknameSaved: "Nome preferido salvo", + avatarShape: "Formato da foto de perfil", + avatarShapeCircle: "Círculo", + avatarShapeRounded: "Arredondado", + chooseSloth: "Ou escolha uma preguiça", + nameSaved: "Nome de perfil salvo", + namePersistErrorTitle: "Não foi possível persistir o nome de perfil", + namePersistErrorDescription: + "Nome atualizado para esta sessão, mas pode não persistir após recarregar.", + photoUpdated: "Foto de perfil atualizada", + photoPersistErrorTitle: "Não foi possível persistir a foto de perfil", + photoPersistErrorDescription: + "Foto atualizada para esta sessão, mas pode não persistir após recarregar.", + photoUpdateErrorTitle: "Não foi possível atualizar a foto de perfil", + imageUseError: "Não foi possível usar esta imagem.", + }, + appearance: { + title: "Aparência", + description: "Como o Unsloth Studio se parece neste dispositivo.", + theme: { + title: "Tema", + label: "Esquema de cores", + description: "Claro, escuro ou seguir o sistema.", + system: "Sistema", + light: "Claro", + dark: "Escuro", + }, + language: { + title: "Idioma", + label: "Idioma de exibição", + description: "O idioma utilizado pelo Unsloth.", + }, + layout: { + title: "Layout", + compactSidebar: "Fixar barra lateral por padrão", + compactSidebarDescription: + "Mantém a barra lateral expandida em vez de recolhê-la em ícones.", + }, + }, + resources: { + title: "Sistema", + description: "Monitore o hardware e o armazenamento deste servidor Studio.", + liveUpdates: "Atualizações ao vivo", + floatingWindow: "Janela flutuante", + disableOverlay: "Desativar sobreposição", + liveMonitor: { + title: "Monitor ao vivo", + cpu: "CPU", + ram: "RAM", + disk: "Disco", + vram: "VRAM", + cpuCores: "{logical} lógicos / {physical} físicos", + currentLoad: "Carga atual", + free: "{value} livres", + noGpu: "Nenhuma GPU visível", + }, + gpu: { + title: "Dispositivos GPU", + noGpu: "Nenhuma GPU visível detectada. Os recursos somente CPU aparecem acima.", + unknownDevice: "GPU desconhecida", + deviceWithIndex: "GPU {index}", + vramUtilization: "VRAM", + used: "{value} usados", + free: "{value} livres", + total: "{value} total", + }, + storage: { + title: "Armazenamento", + systemDisk: "Disco do sistema", + diskUsage: "{used} usados / {total}", + diskFree: "{free} livres", + modelsFolder: "Pasta de modelos", + modelsFolderDescription: "Onde os modelos baixados são armazenados.", + openAction: "Abrir", + copyAction: "Copiar caminho", + copied: "Caminho copiado", + openError: "Não foi possível abrir a pasta", + copyError: "Não foi possível copiar o caminho", + }, + environment: { + title: "Ambiente", + backend: "Backend", + python: "Python", + torch: "Torch", + transformers: "Transformers", + uptime: "Tempo ativo", + processMemory: "Memória do processo", + notInstalled: "Não instalado", + unknown: "Desconhecido", + }, + }, + chat: { + title: "Chat", + description: "Gerencie o histórico de chat armazenado neste dispositivo.", + modelDisclaimer: "Mostrar aviso do modelo", + modelDisclaimerDescription: + 'Mostra "LLMs podem cometer erros" abaixo da caixa de chat.', + artifacts: { + title: "Canvas", + collapseHtmlBlocks: "Recolher blocos HTML", + collapseHtmlBlocksDescription: + "O modo Canvas recolhe o HTML completo automaticamente. Ative isso para também recolher documentos HTML delimitados quando o Canvas estiver desativado.", + allowNetworkAccess: "Permitir acesso à rede no canvas", + allowNetworkAccessDescription: + "Permite que as pré-visualizações do canvas carreguem scripts, estilos, fontes, mídia e recursos de rede de CDNs. Mantenha desativado para pré-visualizações totalmente offline.", + }, + data: "Dados", + exportHistory: "Exportar histórico de chat", + exportHistoryDescription: + "Baixe todos os chats e mensagens em formato JSON.", + exportAction: "Exportar", + exportingAction: "Exportando...", + exportConversations: "Exportar Recentes e Projetos", + exportConversationsDescription: + "Baixe os Recentes ou Recentes mais chats de projetos como JSONL bruto, CSV ou ShareGPT JSONL, combinados ou por chat.", + exportConversationsAction: "Exportar", + exportScopeRecents: "Recentes", + exportScopeAll: "Recentes + Projetos", + exportCombinedSuffix: "(combinado)", + exportPerChatSuffix: "(por chat)", + importChats: "Importar chats", + importChatsDescription: + "Importe um arquivo exportado em JSONL, NDJSON ou CSV para os Recentes.", + importChatsAction: "Importar", + importNoConversations: "Nenhuma conversa encontrada no arquivo.", + importedOneChat: "Importada 1 conversa para os Recentes.", + importedChatCount: "Importadas {count} conversas para os Recentes.", + importFailed: "Falha na importação.", + clearHistory: "Limpar histórico de chat", + clearHistoryDescription: "Exclui o histórico de chat deste dispositivo.", + clearAction: "Limpar", + clearAllChats: "Limpar todos os chats", + clearAllChatsDescription: "Exclui permanentemente todos os chats deste dispositivo.", + noChatsToClear: "Nenhum chat para limpar.", + clearOneChatDescription: + "Exclui permanentemente o único chat deste dispositivo.", + clearChatCountDescription: + "Exclui permanentemente todos os {count} chats deste dispositivo.", + clearChatsAction: "Limpar chats", + clearOneChatTitle: "Limpar 1 chat?", + clearChatsTitle: "Limpar {count} chats?", + clearChatsConfirmDescription: + "Exclui permanentemente todos os chats deste dispositivo. Esta ação não pode ser desfeita.", + clearingAction: "Limpando...", + clearOneChatAction: "Limpar 1 chat", + clearChatCountAction: "Limpar {count} chats", + clearedAllChats: "Todos os chats foram limpos", + clearedOneChat: "1 chat foi limpo", + clearedChatCount: "{count} chats foram limpos", + someChatsCouldNotBeCleared: "Não foi possível limpar alguns chats", + chatsClearedRemainOne: + "{clearedCount} chats limpos; 1 chat restante. Por favor, tente novamente.", + chatsClearedRemain: + "{clearedCount} chats limpos; {remainingCount} chats restantes. Por favor, tente novamente.", + oneChatClearedRemain: + "1 chat limpo; {remainingCount} chats restantes. Por favor, tente novamente.", + oneChatClearedRemainOne: "1 chat limpo; 1 chat restante. Por favor, tente novamente.", + storageClearFailedOne: + "Falha ao limpar o armazenamento; 1 chat pode ter restado. Por favor, tente novamente.", + storageClearFailed: + "Falha ao limpar o armazenamento; {count} chats podem ter restado. Por favor, tente novamente.", + failedToClearChats: "Falha ao limpar os chats", + }, + connections: { + title: "Conexões", + description: "Gerencie provedores e conexões externas.", + }, + apiKeys: { + title: "API", + description: + "Acesse o Unsloth por meio da API compatível com OpenAI.", + readDocs: "Leia a documentação da API", + noAccess: "Nenhum acesso à API ainda.", + newBadge: "Novo", + accessTokens: "Tokens de acesso", + loadError: "Não foi possível carregar o acesso à API.", + createError: "Não foi possível criar o token de acesso.", + revokeError: "Não foi possível revogar o token de acesso.", + never: "Nunca", + tokenNamePlaceholder: "Nome do token (ex: producao)", + newAccessTokenName: "Nome do novo token de acesso", + createToken: "Criar token", + creating: "Criando...", + newTokenCreated: "Novo token de acesso criado", + accessTokenCopied: "Token de acesso copiado", + copyAccessToken: "Copiar token de acesso", + copyNow: "Copie agora - isto não será exibido novamente.", + usageExamples: "Exemplos de uso", + usageTools: "Ferramentas", + exampleCurlTools: "curl + ferramentas", + examplePythonTools: "Python + ferramentas", + exampleJavaScriptTools: "JavaScript + ferramentas", + exampleCurlAdvanced: "curl + avançado", + examplePythonAdvanced: "Python + avançado", + exampleJavaScriptAdvanced: "JavaScript + avançado", + osUnix: "Linux / macOS / WSL", + osWindows: "Windows", + secureHttps: "HTTPS Seguro", + secureHttpsHint: + "A porta 0.0.0.0 ainda está acessível globalmente. Para segurança total, inicie o Unsloth Studio com --secure para expor apenas este link HTTPS.", + copyTunnelUrl: "Copiar URL do túnel", + copySnippet: "Copiar trecho de código", + copy: "Copiar", + copied: "Copiado", + setupDocs: "Docs de configuração:", + relativeNever: "nunca", + relativeJustNow: "agora mesmo", + relativeHoursAgo: "há {count}h", + relativeDaysAgo: "há {count}d", + relativeMonthsAgo: "há {count} meses", + relativeYearsAgo: "há {count} anos", + expired: "expirado", + today: "hoje", + inDays: "em {count}d", + created: "Criado {value}", + used: "Usado {value}", + expires: "Expira {value}", + actionsFor: "Ações para {name}", + copyPrefix: "Copiar prefixo", + revokeToken: "Revogar token", + revokeTitle: 'Revogar token de acesso "{name}"?', + revokeDescription: + "Aplicativos que usam este token perderão o acesso imediatamente. Esta ação não pode ser desfeita.", + revokeAction: 'Revogar "{name}"', + revoking: "Revogando...", + }, + about: { + title: "Sobre", + description: + "Documentação, notas de lançamento, feedback e informações da build.", + studioVersion: "Versão do Unsloth", + packageVersion: "Versão do Pacote", + llamaCppVersion: "Versão do llama.cpp", + hardware: "Hardware", + gpu: "GPU", + cuda: "CUDA", + rocm: "ROCm", + updates: "Atualização", + help: "Ajuda", + documentation: "Documentação", + releaseNotes: "Notas de lançamento", + whatsNew: "O que há de novo", + feedback: "Feedback", + reportIssue: "Reportar um problema", + license: { + sectionTitle: "Licença", + studioLabel: "Unsloth Studio", + studioLicense: "AGPL-3.0", + studioDescription: + "Código aberto sob a licença GNU AGPL v3.0.", + libraryLabel: "Unsloth Core", + libraryLicense: "Apache-2.0", + libraryDescription: "Licenciado sob Apache 2.0.", + }, + dangerZone: "Zona de perigo", + shutDownStudio: "Desligar Unsloth Studio", + shutDownStudioDescription: + "Interrompe o servidor Unsloth e encerra sua sessão.", + shutDown: "Desligar", + update: { + title: "Atualizar Unsloth Studio", + commandText: "Texto de {label}", + copied: "Copiado", + copyCommand: "Copiar comando", + commandCopied: "{label} copiado", + copyNamedCommand: "Copiar {label}", + checkingInstall: "Verificando como o Unsloth foi instalado...", + installIntro: "Para instalar ou atualizar o Unsloth:", + localUpdateHeading: "Atualização local", + installCommandUnix: "Comando de instalação para macOS/Linux", + installCommandWindows: "Comando de instalação para Windows", + localInstallDetected: + "Instalação local detectada. Atualize a partir do seu repositório original para evitar substituí-lo pelo PyPI.", + pullThenUpdate: "Puxe as últimas alterações (git pull) e depois execute o instalador local:", + gitPullCommand: "comando git pull", + localInstallerCommand: "comando do instalador local", + sourceInstallDetected: + "Instalação do pacote por código-fonte ou VCS detectada. Reinstale a partir do caminho local original ou URL do Git.", + repoCheckoutFallback: + "Se você ainda tiver o repositório baixado, execute o instalador local a partir dele:", + restartAfterUpdate: "Reinicie o Unsloth após a atualização.", + desktopManaged: + "O aplicativo de desktop mantém seu backend integrado atualizado e avisará quando uma nova versão estiver disponível.", + unknownInstall: + "Não foi possível detectar como o Unsloth foi instalado. Para instalações via instalador ou PyPI, use os comandos acima.", + localCheckout: + "Para instalações de repositório local, execute o instalador local a partir desse diretório:", + docs: "Docs de instalação:", + docsInstall: "Instalação", + docsUpdating: "Atualização", + docsMac: "Mac", + docsWindows: "Windows", + }, + }, + }, + studio: { + routeTitle: "Treinar", + title: "Estúdio de Fine-tuning", + subtitles: { + configure: "Configure e inicie o treinamento", + trainingInProgress: "Treinamento em andamento", + viewPastRuns: "Visualizar execuções de treino anteriores", + viewingPastRun: "Visualizando execução anterior", + }, + tabs: { + configure: "Configurar", + currentRun: "Execução Atual", + history: "Histórico", + }, + loadingRuntime: "Carregando ambiente de execução de treino...", + backToHistory: "Voltar ao histórico", + sections: { + model: "Modelo", + dataset: "Dataset", + params: "Parâmetros", + training: "Treinamento", + charts: "Gráficos", + progress: "Progresso do Treinamento", + }, + configure: { + title: "Configurar", + description: "Escolha um modelo, dataset e configurações de treinamento.", + startTraining: "Iniciar Treinamento", + starting: "Iniciando...", + loadingModel: "Carregando modelo...", + checkingDataset: "Verificando dataset...", + trainingConfig: "Configuração de Treino", + }, + model: { + title: "Modelo", + description: "Selecione o modelo base e o método de treinamento", + fasterTrainingBadge: "Treinamento 2x Mais Rápido", + baseModel: "Modelo base", + localModel: "Modelo Local", + localModelTooltip: + "Caminho para um modelo baixado localmente ou um repositório HF customizado.", + scanningLocalAndCachedModels: "Escaneando modelos locais e em cache...", + scanning: "Escaneando...", + scanningLocalModels: "Escaneando modelos locais...", + noLocalModelsFound: "Nenhum modelo local encontrado", + noLocalModelsFoundManual: "Nenhum modelo local encontrado. Insira o caminho manualmente.", + failedToLoadLocalModels: "Falha ao carregar modelos locais", + hfCache: "Cache do HF", + customFolders: "Pastas Customizadas", + localDir: "Diretório local", + huggingFaceModel: "Modelo do Hugging Face", + huggingFaceModelTooltip: + "Busque modelos no Hugging Face ou escolha da nossa lista recomendada.", + searchModels: "Buscar modelos...", + searching: "Buscando...", + noModelsFound: "Nenhum modelo encontrado", + needsVram: "Precisa de ~{vram}GB de VRAM (GPU: {gpu}GB)", + tightVram: "~{vram}GB de VRAM (limite na {gpu}GB)", + vramEstimate: "~{vram}GB de VRAM", + method: "Método", + methodTooltip: + "O QLoRA usa quantização de 4 bits para menor uso de VRAM. O LoRA usa 16 bits. O Full atualiza todos os pesos. O CPT (Continued Pretraining) treina em texto bruto para adaptar o modelo a um novo domínio sem formatação de chat.", + readMore: "Leia mais", + fullFineTune: "Fine-tune Completo (Full)", + checkingToken: "Verificando token...", + getOrUpdateToken: "Obter ou atualizar token", + huggingFaceTokenOptional: "Token do Hugging Face (Opcional)", + continuedPretraining: "Pré-treinamento Contínuo (CPT)", + localModels: "Modelos locais", + localModelsFound: "{count} modelos locais/em cache encontrados", + loadingLocalModels: "Carregando modelos locais...", + }, + dataset: { + title: "Dataset", + description: "Selecione ou envie os dados de treinamento", + source: "Origem do dataset", + chooseDataset: "Escolher dataset", + chooseDatasetTooltip: + "Use as abas do pop-up para alternar entre o Hugging Face e as saídas de receitas locais.", + localTab: "Local", + searchHuggingFaceDatasets: "Buscar datasets no Hugging Face...", + searchLocalDatasets: "Buscar datasets locais...", + searching: "Buscando...", + noDatasetsFound: "Nenhum dataset encontrado", + loadingLocalDatasets: "Carregando datasets locais...", + failedToLoadLocalDatasets: "Falha ao carregar datasets locais.", + noLocalDatasetsYet: "Nenhum dataset local ainda.", + noLocalDatasetsMatchSearch: "Nenhum dataset local corresponde à busca.", + openDataRecipes: "Abrir Receitas de Dados", + browsingSource: "Navegando em {browsing}. A seleção atual permanece {current}.", + localDatasets: "Datasets locais", + localDataset: "Dataset local", + localDatasetRows: " / {count} linhas", + huggingFaceDataset: "Dataset do Hugging Face", + localDatasetMetadata: "Metadados do dataset local", + dataRecipeOutput: "Saída da Receita de Dados.", + rows: "Linhas", + columns: "Colunas", + batches: "Lotes", + updated: "Atualizado", + evalDataset: "Dataset de validação (Eval)", + uploading: "Enviando...", + upload: "Upload", + uploadEvalFile: "Enviar arquivo de validação", + evalDatasetDescription: + "Opcional. Se não for fornecido, uma pequena parte será dividida a partir dos dados de treinamento.", + advanced: "Avançado", + targetFormat: "Formato de Destino", + targetFormatTooltip: + "Formato dos seus dados de treinamento. A detecção automática funciona para a maioria dos datasets.", + auto: "Auto", + rawText: "Texto Bruto", + trainSplitStart: "Início da Divisão de Treino", + trainSplitStartTooltip: + "Treine apenas em um subconjunto da sua divisão de treino especificando um índice de linha inicial (inclusivo, baseado em 0). Deixe em branco para começar da primeira linha.", + trainSplitEnd: "Fim da Divisão de Treino", + trainSplitEndTooltip: + "Último índice de linha a ser incluído da divisão de treino (inclusivo, baseado em 0). Por exemplo, defina o Início como 0 e o Fim como 99 para treinar nas primeiras 100 linhas. Deixe em branco para usar todas as linhas restantes.", + endPlaceholder: "Fim", + clear: "Limpar", + dropFileOrClick: "Solte 1 arquivo aqui ou clique para fazer upload", + viewDataset: "Visualizar dataset", + uploadFailed: "Falha no envio", + unknownError: "Erro desconhecido", + unsupportedFileType: "Tipo de arquivo não suportado", + uploadOneFileType: "Envie um arquivo do tipo {types}.", + datasetUploaded: "Dataset enviado", + evalDatasetUploaded: "Dataset de validação enviado", + uploadOneFileAtATime: "Envie um arquivo por vez", + uploadSingleFileDescription: + "O upload do dataset de treinamento aceita apenas um único arquivo.", + checkingToken: "Verificando token...", + getOrUpdateToken: "Obter ou atualizar token", + preview: "Pré-visualizar dataset", + split: "Divisão (Split)", + subset: "Subconjunto (Subset)", + s3: { + title: "Configuração do S3", + description: "Carregue datasets em .parquet, .json, .jsonl ou .csv do Amazon S3", + bucket: "Nome do Bucket", + bucketPlaceholder: "meu-bucket-de-dados-de-treino", + region: "Região da AWS", + regionPlaceholder: "us-east-1", + prefix: "Prefixo do Caminho", + prefixPlaceholder: "datasets/whisper/", + prefixTooltip: "Caminho opcional dentro do bucket para os arquivos do seu dataset", + accessKeyId: "ID da Chave de Acesso", + accessKeyIdPlaceholder: "AKIAIOSFODNN7EXAMPLE", + secretAccessKey: "Chave de Acesso Secreta", + secretAccessKeyPlaceholder: "Sua chave de acesso secreta da AWS", + useIamRole: "Usar Função IAM", + useIamRoleTooltip: "Usa credenciais de função IAM em vez de chaves de acesso (recomendado para EC2/SageMaker)", + testConnection: "Testar Conexão", + connectionSuccess: "Conectado com sucesso ao bucket S3", + connectionFailed: "Falha ao conectar ao bucket S3", + comingSoon: "Integração com S3 em breve", + comingSoonDescription: "O carregamento de datasets do S3 requer o boto3. Este recurso está em desenvolvimento.", + }, + }, + params: { + title: "Parâmetros", + description: "Configure os hiperparâmetros de treinamento", + loraSettings: "Configurações do LoRA", + trainingHyperparameters: "Hiperparâmetros de Treinamento", + maxSteps: "Passos Máximos (Max Steps)", + epochs: "Épocas (Epochs)", + useMaxSteps: "Usar Passos Máximos", + useEpochs: "Usar Épocas", + maxStepsTooltip: "Sobrescreve o total de passos do otimizador.", + epochsTooltip: "Número de passagens completas pelo dataset.", + epochsDescription: "Cada época é uma passagem completa pelo seu dataset.", + maxStepsDescription: + "Limita o treinamento a um número fixo de passos do otimizador.", + contextLength: "Comprimento do Contexto", + contextLengthTooltip: "Número máximo de tokens por amostra de treinamento.", + customContextLength: "Insira um valor personalizado", + contextLengthDescription: "Comprimento máximo de sequência para amostras de treino", + learningRate: "Taxa de Aprendizado (Learning Rate)", + learningRateTooltip: + "Tamanho do passo para atualizações de peso. Valores menores treinam mais lentamente, mas com mais estabilidade.", + learningRateDescription: + "Recomendado: 2e-4 para LoRA, 5e-5 para CPT, 2e-5 para fine-tune completo", + embeddingLearningRate: "Taxa de Aprendizado do Embedding", + embeddingLearningRateTooltip: + "Usado apenas quando o CPT está treinando embed_tokens. Os embeddings são mais fáceis de desestabilizar do que os pesos LoRA, por isso geralmente precisam de um LR menor. Deixe em branco para usar lr/10; a faixa típica de funcionamento é de 2x a 10x menor que o LR principal. Aumente apenas se a adaptação de vocabulário ou de tokens de domínio estiver muito lenta.", + embeddingLearningRateDescription: + "Deixe em branco para usar lr/10 (recomendado). A faixa típica é de 2x a 10x menor que a taxa de aprendizado principal.", + rank: "Rank", + rankTooltip: + "Dimensão das matrizes de baixo rank. Maior = mais capacidade.", + alpha: "Alpha", + alphaTooltip: "Fator de escala para atualizações LoRA. Geralmente o dobro do rank.", + dropout: "Dropout", + dropoutTooltip: + "Probabilidade de dropout para as camadas LoRA para reduzir o overfitting.", + visionLayers: "Camadas de visão", + languageLayers: "Camadas de linguagem", + attentionModules: "Módulos de atenção", + mlpModules: "Módulos MLP", + targetModules: "Módulos de Destino", + enableLora: "Ativar LoRA", + trainWithLora: "Treinar com LoRA", + stableRank: "Stable Rank", + memoryEfficient: "Eficiente em Memória", + optimization: "Otimização", + schedule: "Cronograma", + memory: "Memória", + optimizer: "Otimizador", + optimizerTooltip: + "Algoritmo de otimização. Variantes de 8 bits reduzem o uso de memória. Fused é recomendado para modelos de visão.", + lrScheduler: "Agendador de LR", + lrSchedulerTooltip: + "Como a taxa de aprendizado muda ao longo do treino. Linear decai de forma constante; cosine decai em curva.", + optimizerOptions: { + adamw8bit: "AdamW 8-bit", + pagedAdamw8bit: "Paged AdamW 8-bit", + adamwBnb8bit: "AdamW BNB 8-bit", + pagedAdamw32bit: "Paged AdamW 32-bit", + adamwTorch: "AdamW (PyTorch)", + adamwTorchFused: "AdamW (PyTorch Fused)", + }, + lrSchedulerOptions: { + linear: "Linear", + cosine: "Cosine", + }, + batchSize: "Tamanho do Lote (Batch Size)", + batchSizeTooltip: "Amostras processadas por passo. Maior consome mais VRAM.", + gradAccum: "Acúmulo de Gradiente", + gradAccumTooltip: "Simula tamanhos de lote maiores sem gastar VRAM extra.", + weightDecay: "Decaimento de Peso", + weightDecayTooltip: "Regularização L2 para evitar overfitting.", + warmupSteps: "Passos de Aquecimento (Warmup)", + warmupStepsTooltip: + "Aumenta gradualmente a LR no início do treino para garantir estabilidade.", + scheduleEpochsTooltip: + "Número de passagens completas pelo dataset. Defina 0 para rodar por passos máximos.", + saveSteps: "Passos para Salvar", + saveStepsTooltip: "Salva um checkpoint a cada N passos. 0 para desativar.", + evalSteps: "Passos de Validação", + evalStepsTooltip: + "Fração dos passos totais de treino entre as validações (0-1). Defina como 0 para desativar. Ex: 0.01 = valida a cada 1% dos passos.", + seed: "Seed", + seedTooltip: "Semente aleatória para reprodutibilidade.", + gradCheckpoint: "Grad Checkpoint", + gradCheckpointTooltip: + "Troca processamento por memória recalculando as ativações.", + none: "Nenhum", + standard: "Padrão", + enablePacking: "Ativar empacotamento (packing)", + assistantCompletionsOnly: "Apenas respostas do assistente", + readMore: "Leia mais", + }, + training: { + title: "Treinamento", + description: "Monitore e controle o treinamento", + chartNoDataTitle: "Nenhum dado de treinamento ainda", + chartNoDataDescription: "Inicie o treinamento para ver o progresso da loss", + startTraining: "Iniciar Treinamento", + starting: "Iniciando...", + loadingModel: "Carregando modelo...", + checkingDataset: "Verificando dataset...", + configLabel: "Configuração de Treino", + upload: "Upload", + uploadConfigTooltip: "Carregar uma configuração YAML salva", + save: "Salvar", + saveConfigTooltip: "Baixar configuração atual como YAML", + reset: "Redefinir", + resetConfigTooltip: "Redefinir para os padrões do modelo", + configLoaded: "Configuração carregada", + failedToLoadConfig: "Falha ao carregar a configuração", + invalidYamlFile: "Arquivo YAML inválido", + failedToReadFile: "Falha ao ler o arquivo", + parametersReset: "Parâmetros redefinidos para os padrões do modelo", + audioIncompatible: + "Este modelo não suporta áudio. Mude para um modelo compatível com áudio ou escolha um dataset sem áudio.", + visionIncompatible: + "O modelo de texto não é compatível com um dataset multimodal. Mude para um modelo de visão ou escolha um dataset apenas de texto.", + cancelTitle: "Cancelar Treinamento", + cancelDescription: "Deseja cancelar a execução de treinamento atual?", + continueAction: "Continuar Treinamento", + cancelAction: "Cancelar Treinamento", + stopTitle: "Interromper Treinamento", + stopDescription: "Escolha como você deseja interromper a execução de treinamento atual.", + stopAction: "Interromper", + stopping: "Interrompendo...", + stopAndSave: "Interromper e Salvar", + compareInChat: "Comparar no Chat", + exportModel: "Exportar Modelo", + milestone: "Marco", + halfwayDone: "Metade concluída. O treinamento passou de 50%.", + doneNextStep: + "Treinamento concluído. Próximo passo: comparar as saídas do modelo base vs fine-tuned.", + }, + history: { + title: "Histórico", + emptyTitle: "Nenhuma execução de treino ainda", + emptyDescription: + "Nenhuma execução de treino ainda. Inicie sua primeira execução na aba Configurar.", + loadError: "Falha ao carregar as execuções de treino", + deleteError: "Falha ao excluir a execução de treino. Por favor, tente novamente.", + retry: "Tentar novamente", + loadMore: "Carregar mais", + loading: "Carregando...", + loadingRun: "Carregando execução de treino...", + runNotFound: "Execução não encontrada", + deleteTitle: "Excluir execução de treino?", + deleteDescription: + "Isso excluirá permanentemente esta execução de treino e todas as suas métricas. Esta ação não pode ser desfeita.", + runCount: "{count} execuções", + oneRun: "1 execução", + resume: "Retomar", + resumeTraining: "Retomar treinamento", + resuming: "Retomando...", + deleteRun: "Excluir execução", + loss: "Loss", + steps: "Passos", + lossTrendSparkline: "Minigráfico de tendência da loss", + relativeJustNow: "agora mesmo", + relativeMinutesAgo: "há {count}m", + relativeHoursAgo: "há {count}h", + relativeDaysAgo: "há {count}d", + status: { + completed: "Concluído", + stopped: "Interrompido", + error: "Erro", + running: "Em andamento", + continued: "Continuado", + }, + message: { + completed: "Treinamento concluído", + stopped: "Treinamento interrompido", + running: "Treinamento em andamento", + errored: "Treinamento com erro", + }, + }, + charts: { + settings: "Configurações do Gráfico", + settingsDescription: + "Ajuste a apresentação do gráfico enquanto o treinamento continua rodando.", + openSettings: "Abrir configurações do gráfico", + viewWindow: "Janela de visualização", + viewWindowDescription: "Mostra apenas os passos mais recentes ou o histórico completo.", + window: "Janela", + all: "Tudo", + trainingLoss: "Loss de Treinamento", + trainingLossDescription: "Controle as sobreposições e a suavização EMA.", + smoothing: "Suavização", + smoothingDescription: "Mova para a direita para mais suavização. `0` = bruto.", + showRawLoss: "Mostrar loss bruta", + showSmoothedLoss: "Mostrar loss suavizada", + showAverageLine: "Mostrar linha média", + scaleAndCleanup: "Escala e limpeza", + linear: "Linear", + log: "Log", + noClip: "Sem corte", + clipP99: "Cortar p99", + clipP95: "Cortar p95", + lossAxis: "Eixo da loss", + gradientNormAxis: "Eixo da norma do gradiente", + learningRateAxis: "Eixo da taxa de aprendizado", + resetDefaults: "Redefinir padrões", + loss: "Loss", + smoothed: "Suavizado", + evalLoss: "Loss de Validação", + learningRate: "Taxa de Aprendizado", + lr: "LR", + gradNorm: "Norma do Grad.", + gradientNorm: "Norma do Gradiente", + step: "Passo {step}", + averageValue: "média {value}", + waitingForFirstEvaluationStep: "Aguardando o primeiro passo de validação...", + evaluationNotConfigured: "Validação não configurada", + evalChartWillAppear: "O gráfico aparecerá assim que o eval_steps for alcançado", + setEvalDatasetAndSteps: + "Defina o dataset de validação e eval_steps para acompanhar a loss de validação", + }, + progress: { + title: "Progresso do Treinamento", + liveMetrics: "Métricas de treino em tempo real", + exportGguf: "Exportar para GGUF", + openConfig: "Abrir configuração de treino", + configLabel: "Configuração de Treino", + hyperparams: "Hiperparâmetros", + epochs: "Épocas", + batchSize: "Tamanho do lote", + learningRate: "Taxa de aprendizado", + optimizer: "Otimizador", + maxSteps: "Passos máximos", + contextLength: "Comprimento do contexto", + warmupSteps: "Passos de warmup", + rank: "Rank", + alpha: "Alpha", + dropout: "Dropout", + variant: "Variante", + epoch: "Época {value}", + percentComplete: "{percent}% completo", + stepProgress: "Passo {current} / {total}", + loss: "Loss", + lr: "LR", + gradNorm: "Norma do Grad.", + model: "Modelo", + method: "Método", + elapsed: "Decorrido: {value}", + eta: "ETA: {value}", + stepsPerSecond: "{value} passos/s", + noStepsPerSecond: "-- passos/s", + tokens: "Tokens: {value}", + gpuMonitor: "Monitor da GPU", + live: "Ao vivo", + utilization: "Utilização", + temperature: "Temperatura", + vram: "VRAM", + power: "Energia", + phase: { + idle: "Ocioso", + downloadingModel: "Baixando modelo", + downloadingDataset: "Baixando dataset", + loadingModel: "Carregando modelo", + loadingDataset: "Carregando dataset", + configuring: "Configurando", + training: "Treinando", + completed: "Concluído", + error: "Erro", + stopped: "Interrompido", + }, + }, + trainingStart: { + ready: "Pronto", + downloading: "Baixando", + preparing: "Preparando", + left: "restam {eta}", + downloaded: "{size} baixados", + terminalStart: "> treinamento do unsloth iniciado...", + preparingResources: "> Preparando modelo e dataset...", + gettingReady: "> Estamos deixando tudo pronto para a sua execução...", + waitingForFirstStep: "> {message} | aguardando o primeiro passo... ({step})", + resumingTraining: "Retomando treinamento...", + startingTraining: "iniciando treinamento...", + dataset: "Dataset", + datasetStreaming: "Dataset: streaming (sem download completo)", + modelWeights: "Pesos do modelo", + }, + tour: { + guidedTour: "Tour Guiado", + }, + }, +} as const; diff --git a/studio/frontend/src/i18n/messages.ts b/studio/frontend/src/i18n/messages.ts index ef58ca23fe..23db2ce326 100644 --- a/studio/frontend/src/i18n/messages.ts +++ b/studio/frontend/src/i18n/messages.ts @@ -4,19 +4,26 @@ import { getLocale } from "./locale-store"; import { en } from "./locales/en"; import { zhCN } from "./locales/zh-CN"; +import { ptBR } from "./locales/pt-br"; import { ja } from "./locales/ja"; import type { InterpolationValues, MessageKey } from "./types"; export const LOCALES = { en: { label: "English", nativeLabel: "English" }, "zh-CN": { label: "Chinese (Simplified)", nativeLabel: "简体中文" }, - ja: { label: "Japanese", nativeLabel: "日本語" }, + "pt-BR": { label: "Portuguese (Brazil)", nativeLabel: "Português (Brasil)" }, + "ja": { label: "Japanese", nativeLabel: "日本語" }, } as const; export type Locale = keyof typeof LOCALES; export type TranslationKey = MessageKey; -export const messages = { en, "zh-CN": zhCN, ja } as const; +export const messages = { + en, + "zh-CN": zhCN, + "pt-BR": ptBR, + ja +} as const; const PLACEHOLDER_PATTERN = /\{([a-zA-Z0-9_]+)\}/g; @@ -75,4 +82,4 @@ export function isSupportedLocale(value: unknown): value is Locale { typeof value === "string" && Object.prototype.hasOwnProperty.call(LOCALES, value) ); -} +} \ No newline at end of file diff --git a/tests/studio/install/test_rocm_support.py b/tests/studio/install/test_rocm_support.py index 4c50fa1c8e..092e1803f8 100644 --- a/tests/studio/install/test_rocm_support.py +++ b/tests/studio/install/test_rocm_support.py @@ -1473,12 +1473,14 @@ class TestHardwareAmdBranching: assert "from . import amd" in source def test_hardware_branches_on_is_rocm_for_utilization(self): - """get_gpu_utilization dispatches to amd.py via _smi_query when IS_ROCM.""" + """get_gpu_utilization dispatches visible metrics through amd.py on ROCm.""" hw_path = PACKAGE_ROOT / "studio" / "backend" / "utils" / "hardware" / "hardware.py" source = hw_path.read_text(encoding = "utf-8") func_start = source.find("def get_gpu_utilization") func_body = source[func_start : source.find("\ndef ", func_start + 1)] - assert '_smi_query("get_primary_gpu_utilization"' in func_body + assert "_smi_query(" in func_body + assert '"get_visible_gpu_utilization"' in func_body + assert "_reconcile_rocm_unified_memory" in func_body smi = source[ source.find("def _smi_query") : source.find("\ndef ", source.find("def _smi_query") + 1) ] diff --git a/tests/studio/run_real_mlx_smoke.py b/tests/studio/run_real_mlx_smoke.py index 0843a2b447..7a63dcfb85 100644 --- a/tests/studio/run_real_mlx_smoke.py +++ b/tests/studio/run_real_mlx_smoke.py @@ -565,30 +565,50 @@ def _reload_gguf(save_dir: Path, metrics: dict) -> int: raise SystemExit(f"no .gguf files in {save_dir}") gguf_path = gguf_files[0] + # This is a save/reload-integrity smoke; a few generated tokens are enough. + # Keep llama.cpp bounded on macOS runners where BF16 GGUF decode is CPU-bound. + n_predict = os.environ.get("UNSLOTH_GGUF_RELOAD_N", "8") + n_threads = os.environ.get("UNSLOTH_GGUF_RELOAD_THREADS", str(os.cpu_count() or 4)) + reload_timeout = int(os.environ.get("UNSLOTH_GGUF_RELOAD_TIMEOUT", "420")) + with Phase("reload_gguf", metrics): - proc = subprocess.run( - [ - str(llama_cli), - "-m", - str(gguf_path), - "-p", - PROMPT, - "-n", - "24", - "--temp", - "0", - "--seed", - str(SEED), - "-no-cnv", - "--no-warmup", - ], - capture_output = True, - text = True, - timeout = 300, - # Hand llama-cli an immediate EOF; without it -no-cnv can still leave the - # process blocked reading stdin, which times out instead of generating. - stdin = subprocess.DEVNULL, - ) + argv = [ + str(llama_cli), + "-m", + str(gguf_path), + "-p", + PROMPT, + "-n", + n_predict, + "-t", + n_threads, + "--temp", + "0", + "--seed", + str(SEED), + "-c", + "256", + "--no-warmup", + ] + try: + proc = subprocess.run( + argv, + capture_output = True, + text = True, + timeout = reload_timeout, + # Newer llama.cpp keeps llama-cli in chat mode; exit after one reply. + input = "/exit\n", + ) + except subprocess.TimeoutExpired as exc: + + def _decode(stream) -> str: + if isinstance(stream, bytes): + return stream.decode("utf-8", errors = "replace") + return stream or "" + + print(f" [reload:gguf] TIMEOUT stdout:\n{_decode(exc.stdout)[:1000]}", flush = True) + print(f" [reload:gguf] TIMEOUT stderr:\n{_decode(exc.stderr)[:1000]}", flush = True) + raise metrics["llama_cli_returncode"] = proc.returncode metrics["generation"] = (proc.stdout or "")[:1500]