unsloth/studio/backend/tests
Roland Tannous dbea77e347
Studio: forward llama-server args from unsloth studio run , activate unsloth run , and allow passing model:quant to load models (#5271)
* Studio: forward unknown CLI args directly to llama-server

`unsloth studio run --model X --top-k 20 --chat-template-file foo.jinja`
now passes the unknown flags through to the llama-server subprocess.
Adds a denylist for flags Studio manages (port, -m, -c, --api-key, -ngl,
--flash-attn, --no-context-shift, --jinja, GPU-fit, model-identity, ...)
that returns HTTP 400 on collision. HTTP callers can supply the same
list via LoadRequest.llama_extra_args.

* Studio: accept `--model org/repo:variant` shorthand in `unsloth studio run`

Mirrors llama.cpp's `-hf <repo>:<quant>` and ollama's pull syntax so
`unsloth studio run --model unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL` is
equivalent to `--model unsloth/... --gguf-variant UD-Q4_K_XL`. Local
paths and Windows drive letters are preserved verbatim. If both an
embedded variant and an explicit `--gguf-variant` are given and they
disagree, the command fails with a clear error.

* Studio: register `unsloth run` as alias for `unsloth studio run`

Top-level `unsloth run --model ...` is now equivalent to
`unsloth studio run --model ...`. Same context_settings, so unknown
flags continue to pass through to llama-server.

* Studio: let users override soft-managed llama-server flags from CLI

Trims the denylist to flags Studio fundamentally cannot share with
the user (model identity, --host/--port/--path/--api-prefix,
--api-key, --ssl-*, --webui, --models-*). Soft-managed flags --
-c/--ctx-size, --parallel, --flash-attn, --no-context-shift,
--jinja, -ngl, -t/--threads, --fit* -- now pass through and override
Studio's auto-set version via llama.cpp's last-wins CLI parsing.

Lets users tune their run on the spot:
  unsloth run --model X -c 131072 --parallel 1 --threads 32

* Studio: accept `-hf` / `-hfr` / `--hf-repo` as aliases for `--model`

Matches llama-server's `-hf <repo>:<quant>` spelling so users coming
from llama.cpp can use the same flag. Typer claims the aliases before
the pass-through validator runs, so the HTTP-API denylist on those
flags is unaffected.

  unsloth run -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
2026-05-04 17:08:04 +04:00
..
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
conftest.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
test_anthropic_messages.py Studio: support images on /v1/messages (Anthropic-compat) (#5128) 2026-04-22 03:25:07 +04:00
test_browse_folders_route.py Studio: add folder browser modal for Custom Folders (#5035) 2026-04-15 08:04:33 -07:00
test_cache_case_resolution.py Add tests for cache case resolution (from PR #4822) (#4823) 2026-04-03 13:58:26 -07:00
test_cached_gguf_routes.py Studio: support GGUF variant selection for non-suffixed repos (#5023) 2026-04-15 15:32:01 +04:00
test_data_recipe_github_progress.py Studio: add github_repo seed reader and GitHub Support Bot recipe (#5169) 2026-04-24 12:02:03 -07:00
test_data_recipe_seed.py fix(seed): disable remote code execution in seed inspect dataset loads (#4275) 2026-03-13 19:37:43 +04:00
test_desktop_auth.py Studio: fix 7 failing studio_unit_tests on main (#5216) 2026-04-28 22:43:44 -07:00
test_export_log_cursor.py studio: stream export worker output into the export dialog (#4897) 2026-04-14 08:55:43 -07:00
test_gpu_selection.py Studio: fix 7 failing studio_unit_tests on main (#5216) 2026-04-28 22:43:44 -07:00
test_gpu_selection_sandbox.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00
test_host_defaults.py Default Studio host to 127.0.0.1 and prompt before auto-start (#5267) 2026-05-04 13:03:16 +04:00
test_kv_cache_estimation.py Tests for architecture-aware KV cache estimation (#4760) 2026-04-01 06:13:37 -07:00
test_llama_cpp_cache_aware_disk_check.py Studio: make GGUF disk-space preflight cache-aware (#5012) 2026-04-14 08:53:37 -07:00
test_llama_cpp_context_fit.py Studio: honor explicit GGUF ctx and default to 4096 when weights exceed VRAM (#5011) 2026-04-14 08:53:25 -07:00
test_llama_cpp_load_progress.py Studio: live model-load progress + rate/ETA on download and load (#5017) 2026-04-14 09:46:22 -07:00
test_llama_cpp_load_progress_live.py Studio: split model-load progress label across two rows (#5020) 2026-04-14 10:58:16 -07:00
test_llama_cpp_load_progress_matrix.py Studio: split model-load progress label across two rows (#5020) 2026-04-14 10:58:16 -07:00
test_llama_cpp_max_context_threshold.py Studio: anchor ctx-slider warning threshold at 4096 when weights exceed VRAM (#5014) 2026-04-14 08:53:49 -07:00
test_llama_cpp_no_context_shift.py Studio: hard-stop at n_ctx with a 'Context limit reached' toast (#5021) 2026-04-14 10:58:20 -07:00
test_llama_server_args.py Studio: forward llama-server args from unsloth studio run , activate unsloth run , and allow passing model:quant to load models (#5271) 2026-05-04 17:08:04 +04:00
test_models_get_model_config_case_resolution.py Add tests for cache case resolution (from PR #4822) (#4823) 2026-04-03 13:58:26 -07:00
test_native_context_length.py Studio: Fix chat template disappearing after browser refresh (#5209) 2026-05-01 08:19:09 -07:00
test_openai_tool_passthrough.py Studio: Fix image-only chat requests failing validation (#5212) 2026-04-28 14:49:13 -07:00
test_pytorch_mirror.py Add configurable PyTorch mirror via UNSLOTH_PYTORCH_MIRROR env var (#5024) 2026-04-15 11:39:11 +04:00
test_responses_api.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
test_responses_tool_passthrough.py Studio: forward standard OpenAI tools / tool_choice on /v1/responses (Codex compat) (#5122) 2026-04-21 13:17:20 +04:00
test_studio_api.py Studio: forward standard OpenAI tools / tool_choice to llama-server (#5099) 2026-04-18 12:53:23 +04:00
test_trained_model_scan.py [Studio] Show non exported models in chat UI (#4892) 2026-04-14 15:03:58 +04:00
test_training_worker_flash_attn.py Add Qwen3.6 support (#5257) 2026-05-02 23:30:57 +04:00
test_transformers_version.py split venv_t5 into tiered 5.3.0/5.5.0 and fix trust_remote_code (#4878) 2026-04-07 20:05:01 +04:00
test_utils.py Add AMD ROCm/HIP support across installer and hardware detection (#4720) 2026-04-10 01:56:12 -07:00
test_vision_cache.py Studio: split vision-cache exception test to match transient vs permanent (#5145) 2026-04-23 00:22:40 -07:00
test_vram_estimation.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00