494 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 54a396586e [Mini-VLLM] Repair test suite after SM86 cut
- Restore example connector, test helpers, and dropped patch tests
- Guard MLA metadata import in the example connector
- Point the PLE test at common.ops.ple after upstream #60021 move
- Cut tests for removed features: tools, DRY, epd proxy, STT batch,
  diffusion scheduler, INC/Quark PLE cases, mamba-2 mixer

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 01:06:30 +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
MOVZXandHinata e61dcb9143 [Mini-vLLM] SM86-only cut: models, backends, Rust, tests
- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries
- Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels
- Remove inc/quark quant loaders; keep compressed-tensors and Marlin
- Drop the Rust frontend, pooling entrypoints, and idle test suites
- Rebuild kernels for sm_80;sm_86 and strip the extensions
- Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-18 19:19:56 +07:00
da9134bc89 [ROCm][CI] Give the MoE parallel-launch watchdog room for AITER JIT builds (#62161)
Signed-off-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-17 21:49:27 -05:00
596e530675 [Kernel] Add router GEMM kernels for (5120, 256) and BF16 output to ll_bf16_gemm (#62042)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Lain <fusiyuan2000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
2026-10-16 15:39:46 -07:00
68ebea789a [Perf][MoE] Skip padded work in SM100 FP4 DeepGEMM experts (#59044)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-10-16 16:20:52 -04:00
cffc0cfa31 [CI] Fix B200 FusedMoE Layer Kernels hang on NVSHMEM IB setup (#61695)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-16 12:00:12 -04:00
e711723352 [ROCm] gfx1250 optimizations and model enablement (#58800)
Signed-off-by: jpvillam <juan.villamizar@amd.com>
Signed-off-by: Jaden Mathias <jaden.mathias@amd.com>
Signed-off-by: Juan Villamizar <jpvillam@amd.com>
Signed-off-by: jpvillam <jpvillam@amd.com>
Signed-off-by: Omar Muhammad <omar.muhammad@amd.com>
Signed-off-by: Daniel <danichan@amd.com>
Signed-off-by: Juan Villamizar <100237675+jpvillam-amd@users.noreply.github.com>
Co-authored-by: Jaden Mathias <jaden.mathias@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
Co-authored-by: Omar Muhammad <omar.muhammad@amd.com>
Co-authored-by: Daniel <danichan@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Daniel Chan <Daniel.Chan@amd.com>
2026-10-15 14:51:57 -07:00
Rohan PotdarandClaude Opus 5.5 105605b8e9 [ROCm] Support DeepSeek-V4 hash routing in AITER Triton W4A16 MoE (#60282)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 14:10:12 -05:00
Thien Tran 82b9ccaa79 [Perf][MoE] Skip the TRTLLM fp8-block activation-scale transpose copy (#61773)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
2026-10-15 12:09:07 -07:00
4d58fa254a [MoE] Unify DeepGEMM MegaMoE experts behind one feature-matrix layer; add NVFP4 (#61538)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 19:02:01 +00:00
Mikko TukiainenandCursor 47fd76e4ce [ROCm][Perf] Route softmax MoE top-k, including fused shared-expert sigmoid, through AITER topk_gating (#56226)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-15 17:53:18 +00:00
4f49b55c1f [MoE] Shape-based padding for FlashInfer TRT-LLM MXFP8 experts (gated and non-gated) (#61293)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-10-15 13:44:11 -04:00
Chaitanya Sri Krishna LollaandCursor 833665cded [ROCm][DI] Enable MoRI FP4 dispatch for mxfp4 w4a4 moe (#59596)
Signed-off-by: lcskrishna <lollachaitanya@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-14 23:20:14 -05:00
Shanshan Shen f46021a7fa [ROCm][Perf] Enable DPA+ETP prefill compute/comm dual-batch-overlap for DeepSeek-V4 (#57773)
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Signed-off-by: shen-shanshan <467638484@qq.com>
2026-10-15 11:16:48 +08:00
Kevin H. LuuandOpenAI Codex 0b6d07cbe2 [CI/Build] Use FileStore for DeepEP test rendezvous (#56595)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-10-14 14:29:12 -04:00
2308b6f00b [Perf][MoE] Cheaper triton_kernels 3.8 routing build in the OAI Triton MoE (#58897)
Signed-off-by: Zheng Gong <zgong@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
2026-10-14 10:48:05 +08:00
Chaunceyandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> ad8d39cbab [Bugfix] Fix DSpark graph-padding handling in the DeepSeek-V4.1 MoE fused top-k (#59166)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-14 07:49:52 +08:00
Anirudh Ravichandran e90158d912 [Bugfix][MoE] Clamp BLOCK_SIZE_K to the FP8 quantization block in the batched Triton MoE (#60733) 2026-10-13 17:02:17 -04:00
6849ca696a [Quantization] Add ModelOpt IQ2_XS, IQ2_XXS, and Q8_0 support via b12x (#59604)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Luke Alonso <lalonso@gmail.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Luke Alonso <lalonso@gmail.com>
2026-10-13 09:06:33 -07:00
Elvir Crnčević b9b401b2ef [Kernel] Fuse DeepEP-v2 decode globalize+align into one launch (#53911)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
2026-10-13 11:10:38 -04:00
Vadim GimpelsonandClaude 183625d4f9 [Bugfix] Fall back to auto for unquantized MoE layers when --moe-backend is marlin (#60219)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-13 08:48:13 +00:00
Divakar VermaandClaude Sonnet 5 f7ba007b5e [ROCm][MoE] Split AiterExperts by weight-quantization key (#60322)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-10-13 00:13:33 -05:00
189bbfb9f4 Add MoNe experts pruning support (#50415)
Signed-off-by: Ilya Boytsov <ieboytsov@nebius.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Ilya Boytsov <ieboytsov@nebius.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 23:18:43 +00:00
Shang WangandClaude Opus 5.5 716961cf1f [Bugfix] Drop enable_in_kernel_fc2_reduce from FlashInfer CuteDSL MegaMoE config (#59900)
Signed-off-by: Shang Wang <samshang.wang@mail.utoronto.ca>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 09:05:09 -05:00
Ilya Markov b3ee560ae8 [Bugfix][MoE] Apply expert_map remapping for CUTLASS FP4 MOE expert parallel (#59042)
Signed-off-by: Markov Ilya <markovilya197@gmail.com>
2026-10-12 10:02:56 -04:00
2d69083c4a [ROCm][MXFP4] Align the AITER W4A4 MoE intermediate size to 128 (#55104)
Signed-off-by: xiaofei.zheng <xiaofei.zheng@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
2026-10-10 11:14:01 +08:00
Misha GoinandClaude e3a29aa9b3 [Bugfix][MoE] Size the permute scratch from its inputs (#60447)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-08 15:32:07 -04:00
Divakar VermaandAndreas Karatzas 18751bc6a7 [ROCm][CI] Add coverage for AiterExperts token padding: inf/nan garbage rows (#59334)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-08 19:11:45 +00:00
Misha GoinandClaude 30c7405890 [MoE] MXFP4 oracle: add CUTLASS W4A4 backend and BF16 activation fallback (#60079)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-08 11:39:09 -07:00
stefankoncarevic f4dde3132c [CI][ROCm] Reuse AITER's prebuilt MoE module in the modular-kernel harness (#60633)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
2026-10-08 11:18:05 -05:00
f38c6778ce [quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)
Signed-off-by: Xuanteng Huang <xuantengh@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-10-07 22:01:09 +00:00
Robert ShawandClaude Code 283d76d56a [Bugfix] Widen ep_gather output offset to int64 (#58373)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
2026-10-07 01:45:04 +00:00
Tyler Michael SmithCodexmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
5ab4e4445b [Perf][MoE] Skip padded work in block-FP8 DeepGEMM experts (#59128)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-06 18:49:57 -05:00
40c86ae1ce [Kernel] Enable OAI Triton MXFP4 MoE on SM12x (#58877)
Signed-off-by: lazymio <mio@lazym.io>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
2026-10-06 01:49:13 -04:00
MasonandYongye Zhu 6dd813e0b7 [Bugfix][MoE] Allow MiniMax2 routing in TRTLLM BF16 monolithic backend (#59571)
Signed-off-by: Mason Pitt <bradley.b.pitt@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-10-05 16:24:14 -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
Divakar Verma faa9860dbd [ROCm][CI][AiterExperts] Add test coverage for hidden/intermediate padding correctness (#59333)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2026-10-03 01:53:37 +00:00
Julien Debache 111f71a6db [feat] FlashInfer CuteDSL MegaMoE integration (#54049)
Signed-off-by: jdebache <jdebache@nvidia.com>
2026-10-02 15:43:33 -04:00
9cf087fd14 [Perf] Tune MoE weighted-sum kernel launch configuration (#59731)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
2026-10-02 17:09:29 +00:00
4c4003bb5f [Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 15:50:38 +00:00
5addde2a0a [CPU][Zen] Pass f32 weight scales to the zentorch INT8 MoE (#59434)
Signed-off-by: Ganesh R <Ganesh.R@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
2026-10-01 15:51:53 +08:00
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
Sergey Shlyapnikov 4e1182a3a6 [ROCm][MoE] Pad the AITER MoE intermediate size at allocation time, and round the expert-group count to a kernel that exists (#55368)
Signed-off-by: Sergei Shliapnikov <sergei.shliapnikov@amd.com>
2026-09-30 23:08:21 +08:00
0103a9b96f [Quantization] Add per-token NVFP4 CuTe-DSL MoE backend (#50030)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
2026-09-30 10:42:03 +00:00
Fangzhou AiandCursor Agent 77e8b02c8d [ROCm][Perf] Add opt-in a4w4 (FP4 activation) MoE for DeepSeek V4.1 on AITER (#58819)
Signed-off-by: fai <fangzhouai@gmail.com>
Signed-off-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
Co-authored-by: Cursor Agent (Claude Sonnet 5) <cursoragent@cursor.com>
2026-09-30 15:07:44 +08:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 834ad456d3 [Refactor] Remove dead tests code (#58916)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-30 04:39:03 +00:00
467d81d9a0 [ROCm] Upgrade MoRI version on rocm dockers required for WideEP DP16 DI CI enablement and fixes for combine API (#56073)
Signed-off-by: Shiksha Patel <shiksha.patel@amd.com>
Signed-off-by: lcskrishna <lollachaitanya@gmail.com>
Co-authored-by: shikamd123 <shikpate@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-29 18:07:31 +00:00