27 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
MOVZXandHinata 5f3c7bd8ab [Mini-VLLM] Remove the ROCm device path, debug routes and arch-gated tests
- Delete csrc/rocm, hipify, the _rocm_C extension and the setup.py rocm
  target path; drop the rocm requirement files
- Delete the aiter, rdna3, skinny-gemm and ROCm fused-MoE kernel modules
  and retarget the linear kernel registries away from them
- Reduce platforms/rocm.py to the GCN architecture predicates that live
  code still imports, and delete the RocmPlatform class and plugin
- Drop the VLLM_SERVER_DEV_MODE debug surface: reset, collective_rpc,
  server_info and sleep routes plus the log_error_stack flag
- Delete lm-format-enforcer, lark and otel-semantic-conventions-ai pins;
  the live server process maps none of them
- Delete tests that only build architectures this fork no longer
  registers, and test directories left without any test file
- Restore the tests/v1/kv_connector mock helpers that scheduler tests
  import at module level

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 19:31:07 +07:00
MOVZXandHinata 81074e94a3 [Mini-vLLM] Cut dead subsystems: models, entrypoints, backends, utils, tests
- Drop dead model modules, keeping files live imports require
- Remove anthropic, cohere, codegen entrypoints and batch STT modes
- Delete unused attention backends, MoE experts, and NPU/XPU util leaves
- Strip dead third_party trees and ROCm leaves with no CUDA path
- Remove mooncake EC connectors: dependency missing since branch base
- Re-audit verified by full import sweep and Qwen3.5 smoke test

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 00:20:48 +07:00
ec317a4618 [CI] Keep vLLM log propagation on through the first LLM init in caplog_vllm (#61535)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
2026-10-14 15:10:35 +08:00
Kevin H. LuuandCodex 6a03954b45 [CI] Shard quantization, pooling, multimodal APIs, core kernels and PCP eval automatically (#61477)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-13 16:15:30 -07:00
Ting SUNandCyrus Leung b99fdbe1f8 [Bugfix] Respect the configured offline chat template (#61061)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-10-11 16:27:21 +00:00
wang.yuqi c1692c85f1 [Misc] mv chat_utils.py to renderers. (#60522)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-10-10 06:50:34 +00:00
wang.yuqi 459764104d [Frontend] Move offline_utils.py to entrypoints/common. (#58052)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-10-08 09:56:05 +00:00
Wentao Ye f700178f90 [Refactor] Remove dead env and config (#59781)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-10-02 18:07:20 +00:00
Harry MellorandClaude Opus 5.5 fc2c801ad9 Disable mypy arg-type and assignment checks in tests (#59428)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 15:18:50 +00:00
5225f1bacb [MyPy][3/N] Fix MyPy errors in test groups (part 3) (#55939)
Signed-off-by: Taimys <ffy2281693949@gmail.com>
Signed-off-by: Luyi Xiao <81631911+luyixiao95@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Luyi Xiao <81631911+luyixiao95@users.noreply.github.com>
Co-authored-by: Taimys <ffy2281693949@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 11:06:07 +00:00
Juan Pérez de AlgabaandCursor 31f2e70cd3 [Security] Gate per-request multimodal processor kwargs (#58830)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-26 11:10:35 +00:00
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
summer a85d0738da [Bugfix] Fix double BOS in LLM.chat() for multimodal models (#55288)
Signed-off-by: summer <128961079+zhang-keliang@users.noreply.github.com>
2026-09-04 14:23:15 +00:00
Jan Kwieciński ec32f669bb [Feature][MM_UUIDs] Allow empty video URLs when using multi-modal UUIDs (#54220)
Signed-off-by: Jan Kwiecinski <jkwiecinski@nvidia.com>
2026-09-01 05:55:27 +00:00
Andreas Karatzas b96bcd0b47 [ROCm][CI] Solidify entrypoint LLM lifecycle (#51280)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-08-13 12:24:02 -05:00
Kevin H. LuuandOpenAI Codex 8eb35c5217 [CI] Mirror external test assets in vLLM S3 (#52064)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-08-13 02:08:59 +00:00
Andreas KaratzasandOpenAI Codex 1ab2801dde [ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-08-11 14:19:16 -04:00
Nicolò Lucchesi 8700f86a70 [CI] Fix tests/entrypoints/multimodal/openai/chat_completion/test_audio.py::test_chat_streaming_audio (#50451)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-07-30 16:18:53 -07:00
Zach Zhu 58f9659397 [Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)
Signed-off-by: Zach Zhu <zzqshu@126.com>
2026-07-29 04:20:40 +00:00
Andreas Karatzas 176256b962 [ROCm][CI] Stabilize ROCm audio streaming test (#50163)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
2026-07-29 07:58:10 +08:00
Harry MellorandAndreas Karatzas ca0defa343 Make bare hugging_face imports forbidden (#49726)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-25 04:18:39 -07:00
7513d071bd [ROCm][CI] Fix XPASS(strict) on mixed audio embeds test (#49733)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-24 16:09:18 -05:00
75ccdf3145 [Core] Update PyTorch to 2.13.0, torchvision to 0.28.0, triton to 3.7.1 (#48155)
Signed-off-by: Andrey Talman <atalman@users.noreply.github.com>
Co-authored-by: Andrey Talman <atalman@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-23 11:09:36 -07:00
Andreas Karatzas db28ae2d07 [ROCm][CI] Explicitly tear down multimodal offline LLMs (#46999)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-06-29 07:59:24 +00:00
wang.yuqi 93ee4cd47f [CI] Consolidate multimodal entrypoint tests. (#44819)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-08 04:48:08 -07:00