Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• 234860399b [Frontend][Core] Revert "Add shutdown timeout" (#34730 and #36270) (#36628) Mark McLoughlin 2026-03-10 13:20:41 +00:00
• c88510083b Fix Qwen2.5-VL test for Transformers v5 (#36532) Harry Mellor 2026-03-10 12:05:34 +00:00
• 4ff8c3c8f9 [BUGFIX][Mamba][Qwen3.5] Zero freed SSM cache blocks on GPU (#35219) Vadim Gimpelson 2026-03-10 14:32:20 +04:00
• 507ddbe992 feat(grpc): extract gRPC servicer into smg-grpc-servicer package, add --grpc flag to vllm serve (#36169) Chang SuandNick Hill 2026-03-10 03:29:59 -07:00
• ddbb0d230a [Model Runner V2] Fix mm input embeddings lookup (#36588) Nick Hill 2026-03-10 00:24:58 -07:00
• 9efc3bdcd6 [Model Runner V2] Fix _compute_slot_mappings_kernel for chunked prefill (#36580) Nick Hill 2026-03-10 00:23:42 -07:00
• 156e33553c Fix: Re-Enable EP for trtllm MoE FP8 backend (#36494) amirkl94 2026-03-10 08:11:27 +02:00
• d0cd736caa [Bugfix] Fix RuntimeError: Already borrowed that degrades VLM serving throughput under concurrent load. (#36557) halleriteandCyrus Leung 2026-03-09 22:30:51 -07:00
• 195c997203 Fix LFM2 MoE test for Transformers v5 (#36534) Harry Mellor 2026-03-10 05:29:17 +00:00
• 04b67d8f62 Remove unused disable_fallback field (#36546) Zhuohan Li 2026-03-09 20:56:54 -07:00
• 7279374f91 [Perf] Compute maxsim in worker side, reducing redundant copies, 2.7% E2E throughput improvement (#36159) Wentao Ye 2026-03-09 23:55:58 -04:00
• 006aea17d7 [BugFix] Remove incorrect assert in split_decodes_and_prefills (#36553) Woosuk Kwon 2026-03-09 20:02:02 -07:00
• 0836be3b03 [Model] Add HyperCLOVAX-SEED-Think-32B vision-language model support (#31471) Hojin YangandCyrus Leung 2026-03-10 11:59:19 +09:00
• 4e95ec111c [Bugfix] Fix Qwen3-Next in_proj_ba weight sharding with TP > 1 (#36242) Ajay Anubolu 2026-03-09 19:16:26 -07:00
• 179547d62c [ROCm][CI] Fix ROCm GPT-OSS Eval test group (#36179) Andreas Karatzas 2026-03-09 19:55:20 -05:00
• f85b4eda3a [bugfix] fix nvlink for nixl/ucx (#36475) youkaichao 2026-03-10 07:49:47 +08:00
• 2a194ddd72 [Model Runner V2] Add model_state inputs to CUDA graph capture (#36544) Woosuk Kwon 2026-03-09 15:14:51 -07:00
• 203a7f27da add nemotron v3 reasoning parser (#36393) Shaun Kotekandroot 2026-03-10 00:11:41 +02:00
• 483463f735 [MRV2] Extensible CG dispatch rework (#35959) Lucas Wilkinson 2026-03-09 16:58:45 -04:00
• 4e571ce643 [MTP][Misc] Clean up dead code (#36507) Matthew Bonanni 2026-03-09 14:43:06 -04:00
• 4ff9b045fe [ROCm][CI] Prep Tests For Change To ROCM_ATTN As New Default Backend On ROCm (#36025) Micah Williamson 2026-03-09 13:27:55 -05:00
• 3fd03f1ec2 [BE] Rename should_torch_compile_mm_vit to should_torch_compile_mm_encoder (#36281) Lucas Kabela 2026-03-09 11:22:05 -07:00
• 10a5f4d53d [Model Runner V2] Use NamedTuple for execute_model_state (#35930) Woosuk Kwon 2026-03-09 11:17:34 -07:00
• fe0c085c28 [Docs] Remove the reo beacon (#36528) Simon MoandCursor Agent 2026-03-09 11:16:50 -07:00
• 8d6b3d5dda [Misc] Refactored 5 duplicate helper functions that were copied-pasted across multiple parsers (#36436) Taneem Ibrahim 2026-03-09 14:14:11 -04:00
• 4b87ffbefb [torch.compile] Rename compile_ranges_split_points to compile_ranges_endpoints (#36027) 4 people 2026-03-09 18:04:40 +00:00
• fa028207aa Fix/resupport nongated fused moe triton (#36412) +1222 people 2026-03-09 20:01:18 +02:00
• d460a18fc6 [Docs] Expand --allowed-media-domains security guidance with threat details (#36506) Russell Bryant 2026-03-09 13:43:42 -04:00
• 6e956d9eca [Model Runner V2] Add dummy profile_cudagraph_memory API (#36520) Woosuk Kwon 2026-03-09 10:20:13 -07:00
• 1e0f917b34 [ROCm][CI] Fix logprob divergence for TitanML/tiny-mixtral under AITER rms_norm (#36101) Andreas Karatzas 2026-03-09 12:07:44 -05:00
• c174d54f86 [ROCm][CI] Fix ROCm attention backend validation for head sizes, block sizes, and compute capability checks (#36292) Andreas Karatzas 2026-03-09 12:02:41 -05:00
• 55d27cca55 [Misc] fix typo: dependant -> dependent (2 lines change) (#36511) SoluMilken 2026-03-10 01:00:12 +08:00
• 580864d81e [Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917) Roberto L. Castro 2026-03-09 17:50:36 +01:00
• 2b28b9b269 [Attention][Perf] Optimize cp_gather_and_upconvert_fp8_kv_cache - DeepSeek-v3.2 (#35290) Roberto L. CastroandClaude 2026-03-09 17:46:57 +01:00
• 70485a11bd [ROCM] Optimize the fused_topk_bias to use aiter instead of fallback torch ops. (#36253) Taoyu Zhu 2026-03-10 00:30:35 +08:00
• 74a9f54cdb [CI] Fix edge case that could lead to broken docs builds on main (#36515) Harry Mellor 2026-03-09 16:06:19 +00:00
• 00c4cb5606 [Bugfix] Clear stale CG keys after memory profiling (#36416) Matthew Bonanni 2026-03-09 11:56:00 -04:00
• 941e52c298 [Refactor] Simplify chat_completion_full_generator for tool parsers (#35634) Wentao Ye 2026-03-09 11:33:46 -04:00
• be292b7c14 [Bug] Fix pooling model benchmark script (#36300) Wentao Ye 2026-03-09 11:17:45 -04:00
• 77a73458e3 Reapply [Attention] Refactor check_and_update_config (#35122) Matthew Bonanni 2026-03-09 10:17:14 -04:00
• 5578f2a4d3 Support online use_audio_in_video (#36319) Tianyu GuoandIsotr0py 2026-03-09 22:16:44 +08:00
• 3ec2115015 [Frontend] Move warmup into Renderer (#36482) Cyrus Leung 2026-03-09 21:03:21 +08:00
• b0906d8b02 [MM Encoder] Default to use TORCH_SDPA backend for ViT on Volta/Turing GPU (#36472) Isotr0py 2026-03-09 18:43:44 +08:00
• aaf5fa9abf [ci] Bound openai dependency to 2.24.0 (#36471) Kevin H. Luu 2026-03-09 03:43:26 -07:00
• f96c3ab08c [Deprecation][1/2] Remove items deprecated in v0.18 (#36470) Cyrus Leung 2026-03-09 18:43:23 +08:00
• dc6b578466 [Kernel] Add fused_sigmoid_gating_delta_rule_update kernel for Qwen3 Next (#35777) Xin Yang 2026-03-08 23:41:01 -07:00
• 1bc9c77f6d [XPU] Add test script of PD disaggregation (#36434) liuzhenwei 2026-03-09 13:50:27 +08:00
• 65a4da1504 [Frontend] Add Support for MM Encoder/Decoder Beam Search (Online Transcriptions) (#36160) Alex Brooks 2026-03-08 23:46:23 -06:00
• 217f27598d [Bugfix] Avoid to replace non-tensor members in cpu model runner (#36430) Li, Jiang 2026-03-09 13:06:28 +08:00
• fff3711a24 [Frontend][2/n] Improve pooling entrypoints | embed. (#36110) wang.yuqi 2026-03-09 11:42:19 +08:00
• c4d859c274 [Bugfix] Skip out-of-stage layers in get_layers_from_vllm_config for pipeline parallel (#36243) Tushar Shetty 2026-03-09 09:10:16 +05:30
• 747431044d feat(attention): extract KV-cache update from FlexAttention backend (#36263) cong-or 2026-03-09 03:40:12 +00:00
• d62856b928 [Misc] Move processors to transformers_utils (#35953) Cyrus Leung 2026-03-09 11:31:39 +08:00
• bd2659a566 Increase Flexibility for OOV Multimodal Token Handling (#34858) Alex Brooks 2026-03-08 21:30:49 -06:00
• 90512b2e8b fix: Use iterator as not to store all the file loads in memory at once (#36149) Shaun Kotek 2026-03-09 05:25:21 +02:00
• dcf8862fd4 [Examples][1/n] Resettle basic examples. (#35579) 3 people 2026-03-09 11:22:53 +08:00
• 43aa389231 [Bugfix] Fix CPU OMP autobind assertion to use local_world_size (#35815) 3 people 2026-03-09 11:07:29 +08:00
• 384425f84e [Dependency] Remove default ray dependency (#36170) Wentao Yeandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2026-03-08 23:06:22 -04:00
• a0f44bb616 Allow markdownlint to run locally (#36398) Harry Mellor 2026-03-09 03:05:24 +00:00
• fde4771bbd [XPU][Doc] update xpu document about triton dependency/conflict issue. (#36301) Kunshang Jiandcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> 2026-03-09 10:09:22 +08:00
• e5ff140216 [cudagraph] fix cudagraph warning in deepseekv32 (#28044) Jiangyun Zhu 2026-03-09 08:27:41 +08:00
• 0a6a3a1290 Add support for ModelOpt MXFP8 MoE models (#35986) danisereb 2026-03-08 22:00:05 +02:00
• 4497431df6 [Frontend] Add GPU-less render serving path (vllm launch render) (#36166) Sage 2026-03-08 17:35:09 +02:00
• b7332b058c [Model] Nano Nemotron VL - fast media preprocessing (#35657) nvnbagrov 2026-03-08 12:04:05 +02:00
• 40077ea3de [CI] fix flaky empty responses and add diagnostic assertions in vision chat tests (#36341) Andreas Karatzas 2026-03-08 00:42:24 -06:00
• 5d6aae4577 [LMCache MP Patch]: Race Condition + Duplicated Block Ids (#35831) Samuel Shen 2026-03-07 13:52:48 -08:00
• 63298ee173 [Bugfix][LMCache][KVConnector] fix potential memory leak in LMCache multiprocess mode (#35931) Roy Huang 2026-03-07 13:52:35 -08:00
• 2dde535df1 [compile] Split compile/warmup monitoring (#36098) Richard Zou 2026-03-07 16:52:11 -05:00
• 379689d533 [Perf] Support FP8 KV cache for Flashinfer MLA Sparse (#35891) Wei Zhao 2026-03-07 16:51:54 -05:00
• a6be75dbd2 [Core] NGram GPU Implementation compatible with Async Scheduler (#29184) PatchyTIS 2026-03-08 05:51:37 +08:00
• ee54f9cdb9 [ROCm][CI] Accept Different But Valid Output for test_olmoe_tp (#35224) Micah Williamson 2026-03-07 15:50:52 -06:00
• fc4657756f [ROCm][CI] Enable AITER for failing test_gpt_oss test case on MI355 (#36174) Micah Williamson 2026-03-07 15:50:17 -06:00
• eebd14651f [CI] Enable Crosslayer KV layout tests for ROCm platforms (#35416) qli88 2026-03-07 15:49:56 -06:00
• ebb9cc5f2b [UX][Startup] Account for CUDA graphs during memory profiling (#30515) Matthew Bonanni 2026-03-07 16:49:23 -05:00
• 85f50eb41f Adding support to Sarvam's MoE models (#33942) rahul-sarvam 2026-03-08 01:16:24 +08:00
• 5261223c2d [Misc] Remove duplicate parser registration (#36303) Taneem Ibrahim 2026-03-07 08:37:01 -06:00
• 00b814ba5a [V0 Deprecation] Remove unused swap_space parameter (#36216) lifandmcelrath 2026-03-07 22:09:55 +08:00
• ee8a29511f [Bugfix] Fix compressed-tensors quantization failure for DeepSeek-R1 on MI300x (#36247) vllmellm 2026-03-07 17:26:59 +08:00
• 755356b3d1 feat: expose media_io_kwargs at runtime (#34778) milesial 2026-03-06 20:27:04 -08:00
• 58928475e4 [ROCm][CI] Making entrypoints more deterministic on ROCm (#36293) Andreas Karatzas 2026-03-06 21:04:40 -06:00
• 1a9718085c Fix CUDA graph decode capture crash in AITER FlashAttention (#36042) Mengtao (Martin) YuanandMartin Yuan 2026-03-06 18:12:07 -08:00
• 7eb524e64c refine vllm bench throughput --backend hf (#35971) Kunshang Ji 2026-03-07 10:10:33 +08:00
• c7f32e08c2 [BugFix] Avoid ignored trust_remote_code warnings (#36290) Nick Hill 2026-03-06 17:24:18 -08:00
• b354686524 [Model Runner V2] Fix warmup for pipeline parallel (#36280) Nick Hill 2026-03-06 16:58:51 -08:00
• 6a18d8789b [Core] Fix benign error log during normal shutdown (#36270) Nick HillandMark McLoughlin 2026-03-06 16:39:21 -08:00
• 24a03915f5 mla: don't update kv cache on dummy forwards (#36282) Itay Alroy 2026-03-07 02:36:00 +02:00
• b5e34e1fca [ROCm][CI] Fixing yaml file for external amd-ci signal (#36284) Andreas Karatzas 2026-03-06 18:30:39 -06:00
• ce8546a12b [docs][torch.compile] Add fusions.md — kernel/operator fusion reference page (#35538) 6 people 2026-03-06 23:55:06 +00:00
• c188749bcd [ROCm] Support MLA with nhead<16 and FP8 KV cache for TP=8 (Kimi K2.5/Linear) (#35850) Chuan (Richard) Li 2026-03-06 12:24:03 -08:00
• 225d1090a0 Enabling some B200-specific tests on MI355 (#35253) Alexei-V-Ivanov-AMD 2026-03-06 13:27:20 -06:00
• f3c6c9c9d7 [CustomOp] CustomOp FusedRMSNormGated (#35877) eellison 2026-03-06 13:53:37 -05:00
• 26bd43b52d Revert "[BugFix] Fix engine hanging after KV cache initialization fai… (#36262) Nick Hill 2026-03-06 08:28:09 -08:00
• 6b625a8807 [Bugfix] Quickfix followups to busy loop removal in #28053 (#36068) Travis JohnsonandNick Hill 2026-03-06 09:13:05 -07:00
• 54756b6109 [compile] Stop unconditionally patching constrain_to_fx_strides (#36152) Richard Zou 2026-03-06 10:17:27 -05:00
• 39f9ea0da4 [Bugfix] Fix cudagraph_mode:FULL dispatch (This does not impact FULL_AND_PIECEWISE (default)) (#36165) Raphaël Rialland 2026-03-06 15:15:31 +01:00
• e4ae148a78 [Refactor] Modular video loader backend refactoring (#35202) Isotr0py 2026-03-06 22:06:59 +08:00
• 1d0c0d209c [Misc] Lazy import registered processors (#36024) Isotr0pyandRoger Wang 2026-03-06 22:06:45 +08:00
• fcb73f306c [bugfix] add api process rank in default multimodal request (#36150) Chenguang Zheng 2026-03-06 20:00:09 +08:00
• e2090bf3af [CI] Fix startup error test (#36230) Harry Mellor 2026-03-06 11:50:28 +00:00
• 2a00d3241f [CI][MM] Gate vision encoder attention mask to MiniCPM only, fixing Aria regression (#36206) Andreas Karatzas 2026-03-06 03:17:08 -06:00