14 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
roikoren755andmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 51eeb0c58f [Bugfix] Load stacked expert weights for non-gated MoE (#59031)
Signed-off-by: Roi Koren <roik@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-05 15:26:55 +03:00
Willian Zandmgoin ad6817b68d [Perf][MoE] Index expert mapping lookups in RoutedExperts.load_weights (#58720)
Signed-off-by: Willian <willian@willian.email>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2026-09-26 06:48:24 -07:00
Misha Goin ac78445bc9 [MoE] Encapsulate TRT-LLM BF16 weight layout handling (#57405)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-09-17 17:47:30 -04:00
78fdf4efb8 [Bugfix][MoE] Convert FlashInfer BF16 weights in place (#54699)
Signed-off-by: Yuchen Wang <93700456+yuchenwang3@users.noreply.github.com>
Signed-off-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
2026-09-17 22:00:04 +08:00
Andreas Karatzasandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 36f4630d89 [Bugfix][MoE] Fix fused block-scale orientation (#50727)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-11 16:05:38 -04:00
Isotr0py 073c510c91 [Migration] Migrate bitsandbytes support to OOT plugin (#43529)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
2026-08-09 10:27:31 +08:00
Walter Beller-MoralesandHarry Mellor 70456e5e6f [Bugfix] when loading weights skip empty expert bias if model does not support them (#50937)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-08-07 12:45:52 -07:00
Harry MellorClaude Opus 5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
94e9ef0768 [Bugfix] Don't transpose fused MoE quantization scales in RoutedExperts.load_weights (#50137)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-31 08:46:52 -07:00
bnellnmandHarry Mellor 6e311c6e20 [MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-07-31 11:28:18 +01:00
c0b2d8f471 [Bugfix] FusedMoE: coerce shape-(1,) per-tensor scales to 0-D scalar … (#43362)
Signed-off-by: Varshith <kvarshithgowda@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2026-06-22 13:26:53 -07:00
bnellnm dc68bd8c41 [MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)
Signed-off-by: Bill Nell <bnell@redhat.com>
2026-06-08 10:42:58 -04:00
fxmarty-amd 4eee77b877 [fix][MOE] Fix MOE experts intermediate_size dimension not being narrowed before weight loading (#39688)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
2026-04-14 09:35:28 +00:00
SandishKumarHN 3896e021a0 [Bugfix] Fix FusedMoE weight loading with padded hidden dimensions (#37010)
Signed-off-by: SandishKumarHN <sandish@fb.com>
2026-03-31 12:22:26 -04:00