599 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 2066d3143f [Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack
- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions,
  rl, render-launcher and batch entrypoints; keep scale-out token routes
- Drop the Swagger static bundle and the /docs, /redoc routes
- Delete device-keyed tuning configs for fused_moe, quant utils, mamba
  select-state and helion; no sm86 entry ever existed for any of them
- Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant
  quantizers and their config, metrics and loader plumbing
- Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu
  requirements and the setup.py cpu target path
- Delete 29 environment variables nothing reads and 14 chat-template
  fallbacks for models this fork no longer registers
- Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark,
  dsv3 gemm) with their kernels, bindings, wrappers and CMake entries
- Delete the connector test suites that targeted removed connectors
- Cut the Mistral tokenizer and parser stack, its tests, and the
  mistral_common and ijson dependency pins
- Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier
  cut deleted while keeping the model tree

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 17:10:56 +07:00
MOVZXandHinata 2b544b7ba0 [Mini-VLLM] Cut dead subsystems across serving, connectors, parsers
- Remove P/D transfer connectors: nixl, nixl_chat, mooncake x2, hf3fs,
  moriio, hisparse, example and hidden-states connectors
- Reduce weight_transfer to the base API used by model loading
- Remove kv_offload tiering, simple_kv_offload, ec cpu/example,
  snapshot command, engine snapshot server
- Remove transformers model fallback, dsv4 tokenizers, dead platforms
  cpu/tpu/xpu, flashmla third_party, dsa, megamoe/flydsl, dead attn
  ops, dead layers (short_conv, fused_embed_norm, indexer_topk,
  relu2 gemma_ar, lightning_attn, minimax_rms_norm), gemm_rs_ar
- Keep MoE LoRA op (imported eagerly by punica_gpu); drop fp8 variant
- Rebuild parser hubs around Qwen3 adapters only (36 dead adapters)
- Remove dead tests with the code they covered

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 02:19:03 +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
MOVZX c5ab42bc0f Merge branch 'main' into patches 2026-10-18 16:04:36 +07:00
2067297b2f [ROCm][Perf] Use AITER tuned configs to select a4w4 gemm kernel instead of env var (#61278)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
Signed-off-by: afriedri <afriedri@amd.com>
Co-authored-by: Simon Danielsson <70206058+simondanielsson@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-10-17 04:00:28 -05:00
MOVZX e0fe5df731 Merge branch 'main' into patches 2026-10-17 08:06:56 +00:00
153a17166e [Frontend] Add the Beam reasoning and tool parsers (#62052)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
Co-authored-by: neilkg <33635204+neilkg@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 14:08:29 -07:00
Dan BlanaruandClaude Opus 5.5 9731f30a03 [Bugfix] Keep VLLM_RAY_BUNDLE_INDICES out of the compile cache key (#61211)
Signed-off-by: DanBlanaru <48605845+DanBlanaru@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 20:59:48 +00:00
MOVZXandHinata 0076adc78b [Qwen3.5] Project the refusal direction out of the residual stream at runtime
orcarouter/Qwen3.8-27B-Uncensored removes refusal by editing weights. The
Swift release we serve is AutoRound W8A16, so re-editing weights means
re-quantizing. Project one unit direction r out of every residual-stream
writer output instead: x <- x - r (r . x), which equals the weight edit
W' = W - r(r^T W) on every writer feeding that stream (Arditi et al. 2024).

Sites: attention output for both the full-attention and GDN branches, the
MLP output, and token embeddings, in Qwen3NextDecoderLayer.forward and
Qwen3NextModel.embed_input_ids, which Qwen3_5DecoderLayer and Qwen3_5Model
inherit but whose base constructors they skip, so both register there too.
The MTP drafter reuses Qwen3_5DecoderLayer and calls its own
embed_input_ids, so the draft path is covered at the same width, and
_maybe_share_embeddings at PP=1 hands the draft the target embedding
module. Sequence parallelism shards dim 0 only, so the last dim is
hidden_size at every site.

VLLM_ABLITERATION names a JSON file with key refusal_direction, a
safetensors tensor, or a bare name resolved under
/opt/qwen38/abliteration then /data/abliteration. Empty or 0 is off.
register() always creates the buffer _abliteration_r, zeros when off, so
one compiled graph serves ON and OFF and toggling the switch
(declared in envs.py, hence in compile_factors) invalidates the compile
cache. project_() is an in-place rank-1 update with no full-size
temporary, and skips tensors whose width is not hidden_size.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-15 21:40:16 +07:00
Talor Abramovich 81e42c9987 [Feature][Frontend] Control the log level of request JSON body using env var (#60630)
Signed-off-by: talora <talora@nvidia.com>
2026-10-15 11:07:19 +00:00
Woosuk KwonandClaude Opus 5.5 e57bb4ace7 [Core] Remove the legacy Ray compiled-graph executor (#61712)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 18:13:27 -07:00
xuebwang 81503550f3 [ROCm] Disable AITER FP8/FP4 BMM for MLA by default (#53123)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
2026-10-14 10:46:02 +00:00
Juan Pérez de AlgabaandOpenAI Codex 7173c64e2e [Security] Bound decoded and downloaded media per request (#61226)
Signed-off-by: juanpas97 <juan.perezalgaba@gmail.com>
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-10-13 10:17:14 +00:00
Fangzhou AiandClaude Opus 5.5 cc2a6eea1a [ROCm][Perf][DSv4.1] Mono decode on every backbone layer (#61082)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 10:16:50 +08:00
AMD-yanfeiwangandaoshen02 e3bbaf2369 [ROCm][DSv4] Fuse the shared expert into AITER MegaMoE (#61004)
Signed-off-by: Yanfei Wang <yanfei.wang@amd.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
2026-10-12 15:53:16 +08:00
93d2cab35e [Security] Fix P2P ZMQ socket exhaustion via unbounded peer sessions (#51504)
Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
2026-10-11 11:39:11 -04:00
Fangzhou AiandClaude Opus 5.5 193922d6ff [ROCm][Perf][DSv4.1] Mono decode layer for DeepSeek-V4.1-Flash on MI355X (#60397)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 20:53:18 -05:00
Hyukjoon LeeandClaude Opus 5.5 2342343746 [ROCm][DCP] Default MLA DCP verify to the round-robin asm decode where it applies (#59965)
Signed-off-by: hyukjlee <hyukjlee@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 03:10:54 +00:00
Ayaan Nadamal 84593955fa [Perf][MoE] Support fp8 combine in FlashInfer one-sided MoE all2all (#57995)
Signed-off-by: Ayaan Nadamal <anadamal@nvidia.com>
2026-10-02 16:29:16 -04:00
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
Ganesh RCursormergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
e12291d733 [CPU][Zen] Add DA8W4 (W4A8) int4 support for dense and MoE layers (#54024)
Signed-off-by: R <Ganesh.R@amd.com>
Signed-off-by: Ganesh R <Ganesh.R@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-01 15:18:25 +08:00
Juan Pérez de AlgabaandCursor cff08b461e [Security] Fix chat template resource-exhaustion DoS (GHSA-4hhp-h66f-… (#50300)
Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-30 08:32:00 -07:00
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
Tyler Michael SmithandCodex 50239dfc4d [WideEP] Change DeepEPv2 to auto select hybrid mode by default (#57991)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-29 18:36:30 -04:00
Mehmet Cagri 70ae0b7435 [ROCm][MLA] Enable sparse MLA Gluon kernel from Aiter (#53492)
Signed-off-by: Mehmet Cagri Kaymak <mehmet.kaymak@amd.com>
Signed-off-by: Mehmet Cagri <mehmet.kaymak@amd.com>
2026-09-29 09:08:18 +08:00
25624f65cf [ROCm][MLA] Add an AITER ASM round-robin decode route for DCP multi-token verify (#56861)
Signed-off-by: Xiaohu Guo <Xiaohu.Guo@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: seungrokj <144636725+seungrokj@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 14:52:21 -04:00
Chao Lei 386ac2573e [Bugfix][KV Connector] Retry Mooncake bootstrap registration on timeout (reopens #55763) (#58919) 2026-09-27 19:47:36 +00:00
Hongxia Yang 3137ff0773 [ROCm][Kimi-K3] Make VLLM_ROCM_USE_AITER_MOE_SITUV2 select a4w4/a8w4/a16w4 (#58201)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
2026-09-27 02:26:49 +00:00
YiSheng5andKunshang Ji b05f7d5fbc [PP][XPU]Add the flag to control microbatch feature on MRV2+PP (#55145)
Signed-off-by: yisheng <yi.sheng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-09-25 12:05:35 +08:00
Misha GoinandCodex 71891bdb94 [Perf] Parallelize registered CUDA Triton kernel warmup at startup (#58582)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-24 19:52:00 -04:00
liuzhenwei dcfc17e0b1 [XPU] enable XPU GRAPH by default (#51600)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-09-24 19:17:25 +08:00
f92b78f6ef [Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-09-22 01:07:17 -07:00
yinfengLiuandShanshan Shen 2af05512cf [Kernel] Add opt-in load-time MXFP4 dequantization (#50814)
Signed-off-by: Liuyinfeng01 <yinfeliu@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
2026-09-22 14:51:12 +08:00
Nicolò Lucchesi 54020c3c3e [Engram] Drop redundant VLLM_PLE_CPU_OFFLOAD env var (#57937)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-21 20:16:02 +02:00
7d99c2c4fd [Feature][Humming] Humming feature integration (#56685)
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2026-09-20 08:11:01 -07:00
shaohuaxiandCodex 67a8a3f926 [Bugfix][CPU] Fix macOS multimodal SHM cache initialization (#57142)
Signed-off-by: 子华 <huaxi.shx@alibaba-inc.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-18 09:05:13 +00:00
afriedri a9a7e45f31 [ROCm] Restore VLLM_ROCM_USE_AITER_FP4_ASM_GEMM and default w4a4 ASM GEMM back to off (#57055)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
2026-09-17 13:39:52 -05:00
Nick Hill 5efbf0886a [CI] Support FORCE_COLOR env var; enable colors in CPU CI output (#56913)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-09-16 22:40:21 -04:00
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
wangxiyuanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 118e17f5ff [Platform] Move env check function to platform interface (#48599)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-16 10:08:36 +00:00
wangxiyuan b0898a4937 [Misc] Allow install empty package from pip (#41074)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2026-09-16 02:02:37 +00:00
ppalangaCursorPoovaiah Palangappamergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Hongxia Yang
a4d2d9d95e [ROCm][Kimi-K3] Enable a4w4 flydsl kernels for KimiK3 (#53940)
Signed-off-by: ppalanga <ppalanga@amd.com>
Signed-off-by: Poovaiah Palangappa <poovaiah.palangappa@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Poovaiah Palangappa <poovaiah.palangappa@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
2026-09-16 01:38:02 +00:00
Martin Hickey 934b1fcbcb [Frontend] Replace VLLM_ENABLE_SCALE_OUT_ENDPOINTS with --enable-scale-out (#55176)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
2026-09-14 10:02:14 +00:00
d2d649e674 [DS V4.1][Engram] Support async prefetch for offloaded engram lookups and engram DP sharding (#56512)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: ywang96 <>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
2026-09-13 02:44:23 -07:00
Itay Alroy 658c8131c7 [Elastic EP] Reuse CUDA graphs across reconfiguration (#54985) 2026-09-12 10:26:39 -04:00
Wentao Ye 5fe77aecfc [Deprecation] Deprecate items scheduled for 0.29 (#55353)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-09-11 08:17:02 -07:00
Simon Danielsson ae48466cf3 [Perf][ROCm] Add AITER custom AG/RS (DP only) (#48247)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
2026-09-11 13:19:57 +08:00