unsloth/studio/backend/core/inference
2026-07-14 22:32:24 -03:00
..
__init__.py
_html_to_md.py
_vulkan_probe.py Studio: add Vulkan llama.cpp support (#5819) 2026-07-09 03:39:48 -07:00
anthropic_compat.py Studio: stream reasoning tokens in the tool-loop generator (fixes DeepSeek thinking not streaming with a pill on) (#6947) 2026-07-07 19:50:40 -03:00
api_monitor.py
audio_codecs.py
chat_eos.py
chat_template_helpers.py Studio: render thinking blocks for safetensors inference with prefilled <think> templates (#6816) 2026-07-08 08:14:03 -07:00
chat_templates.py
defaults.py Add DeepSeek-V4-Flash-GGUF to Studio with none/high/max reasoning (#6908) 2026-07-07 06:13:43 -07:00
external_provider.py
inference.py Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
key_exchange.py
llama_admission.py Studio: queue local GGUF OpenAI-compatible requests before llama-server (#7047) 2026-07-10 17:05:48 -03:00
llama_cpp.py Studio: make Stop interrupt a llama.cpp generation stalled mid-stream (#7117) 2026-07-14 05:11:56 -07:00
llama_http.py
llama_keepwarm.py
llama_server_args.py
llama_stats.py
local_model_resolver.py
mcp_client.py Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
mcp_config_import.py
message_content.py
mlx_inference.py Studio: render thinking blocks for safetensors inference with prefilled <think> templates (#6816) 2026-07-08 08:14:03 -07:00
model_ids.py
orchestrator.py Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
passthrough_healing.py
presence_penalty.py
pricing.py
providers.py
runtime_context.py
safetensors_agentic.py Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
tensor_fallback.py
tool_call_parser.py
tool_loop_controller.py Studio: render image content returned by MCP tools (#7081) 2026-07-14 00:30:21 -07:00
tools.py Sniff unknown MIME types and handle Latin-1 2026-07-14 22:32:24 -03:00
worker.py Studio: install torchao Windows ROCm stub in the inference worker (#7000) 2026-07-13 19:20:25 -03:00