unsloth/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
..
python Fix DPO trainer multi process hang (#5199) 2026-04-29 04:15:34 -07:00
qlora Revert "[pre-commit.ci] auto fixes from pre-commit.com hooks" 2025-12-01 07:24:58 -08:00
saving chore: fix typo cleanup across tests and backend strings (#5152) 2026-04-24 12:51:27 +01:00
sh Default Studio host to 127.0.0.1 and prompt before auto-start (#5267) 2026-05-04 13:03:16 +04:00
studio 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
utils feat: Add cactus QAT scheme support (#4679) 2026-04-15 07:40:03 -07:00
__init__.py Qwen 3, Bug Fixes (#2445) 2025-04-30 22:38:39 -07:00
run_all.sh fix: add tokenizers to no-torch deps and TORCH_CONSTRAINT for arm64 macOS py313+ (#4748) 2026-04-01 06:12:17 -07:00
test_cli_export_unpacking.py studio: stream export worker output into the export dialog (#4897) 2026-04-14 08:55:43 -07:00
test_gemma4_chat_template.py update gema4 chat templates (#5116) 2026-04-22 09:04:08 -07:00
test_get_model_name.py feat: Add support for OLMo-3 model (#4678) 2026-04-15 07:39:11 -07:00
test_loader_glob_skip.py Add unit tests for HfFileSystem glob skip guard (#4854) 2026-04-06 08:54:36 -07:00
test_model_registry.py Revert "[FIX] Vllm guided decoding params (#3662)" 2025-12-01 05:43:45 -08:00
test_peft_weight_converter_compat.py Patch checkpoint reload init functions to strip unsupported args (#5167) 2026-04-29 02:50:49 -07:00
test_raw_text.py fix: check find() return value before adding offset in try_fix_tokenizer (#4923) 2026-04-09 06:15:46 -07:00
test_resolve_model_class.py fix: guard resolve_model_class fallback against unresolvable transformers AutoModel entries (#5155) 2026-04-24 05:59:17 -07:00