18 Commits
Author SHA1 Message Date
MOVZXandHinata 5aa2ac64f8 [Mini-VLLM] Remove LoRA, plugins, speech-to-text and scale-out surfaces
Production runs one static model behind the OpenAI-compatible API. Every
adapter path and non-OpenAI HTTP surface is unreachable there.

- Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the
  scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora
  CLI group, and the LoRA tests.
- Drop the plugin loader in vllm/plugins. Platform resolution is now
  CUDA-only and the general/stat-logger plugin hooks are gone.
- Delete the speech-to-text and realtime entrypoints, the scale-out
  render routes, and vllm/config/speech_to_text.py. GenerationTask is
  generate-only.
- Cut DecodeBenchConnector and the disagg-prefill doc and image. The
  Multi, Offloading and Example connectors stay; production uses the
  CPU KV offload tier.
- Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake
  arch gate, declarations and op registrations. The CUDA build never
  defined the guard and no Python caller existed.
- Delete the orphan Mistral and Pixtral chat fixtures and examples/.
- Fix _check_model: removing the LoRA early return made every request
  fail with "The model ... does not exist. Valid aliases: ...".

Verified on an RTX 3090: import sweep reports 1242 modules with 7 known
optional-dependency failures; a live server answers chat, completions,
responses, tokenize and detokenize with zero log errors and 404 for the
removed surfaces; collection yields 8558 tests with the 3 pre-existing
errors; ruff adds no new finding; the incremental _C build succeeds.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 21:06:19 +07:00
Nick HillandClaude Opus 5.5 c055c1e075 [Core] Include the LoRA path in prefix-cache block hashes (#59335)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 08:37:09 +08:00
Nick HillandClaude Opus 5.5 105a4e097b [Bugfix][Frontend] Reject LoRA adapters named after a served model (#59286)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 18:29:38 -07:00
Harry MellorandClaude Opus 5 651a88c09a [CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 10:57:24 -07:00
Harry MellorandClaude Opus 5 8c1557a79c Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 16:44:29 +00:00
wang.yuqiandCyrus Leung eeb549a74d [Frontend] Move engine/protocol.py out openai folder (#54492)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2026-08-31 10:13:50 +00:00
wang.yuqi b8165e5e58 [Frontend] Consolidate entrypoint exception handler (#52261)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-08-14 09:27:24 +00:00
wang.yuqi 1eb2cc961e [Frontend] Refactor ServingTokenization entrypoint. (#46022)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-22 06:27:58 +00:00
wang.yuqi d01d0b4646 [Frontend] Consolidate online serving utils. (#44479)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-04 06:49:31 +00:00
Jee Jee Li 4d1fd13613 [CI/Build] Fix LoRA testing (#44425)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2026-06-03 08:58:06 -07:00
Jee Jee Ligemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Roger Wang
7d5b033782 [LoRA] Support 2D and 3D MoE LoRA adapter at the same time (#42242)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2026-05-18 15:22:26 +08:00
wang.yuqi 66c079ae83 [Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-04-09 10:09:45 +00:00
Sage 06e0bc21d2 [Frontend] Split OpenAIServingModels into OpenAIModelRegistry + OpenAIServingModels (#36536)
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2026-03-12 03:29:37 -07:00
Ning Xie fe714dd507 [openapi server] log exception in exception handler(2/N) (#36201)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2026-03-10 20:16:30 -07:00
Cyrus Leung b96f7314b4 [Refactor] Pass Renderer to Input Processor (#34329)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-11 19:38:11 -08:00
Cyrus Leung d117a4d1a9 [Frontend] Introduce Renderer for processing chat messages (using ModelConfig) (#30200)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-22 12:44:22 +00:00
Jackmin801andJee Jee Li 12dab78f49 [Feat] allow inplace loading lora (#31326)
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Signed-off-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-01-20 10:15:20 +08:00
Chauncey 4c1c501a7e [Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-01-15 07:41:34 +00:00