iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
16,272 Commits 3 Branches 0 Tags
856ec4804a4e236bdd796e0954094a532c7d19bc
Commit Graph
16272 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Roger WangandCopilot 856ec4804a [DSv4] Tune default value of VLLM_MULTI_STREAM_GEMM_TOKEN_THRESHOLD (#41526) 
Co-authored-by: Copilot <copilot@github.com>
 2026-05-02 18:32:09 -07:00
Yongye Zhu 1c607d7b2c [DSV4] Guard megamoe flag with Pure TP (#41522) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
 2026-05-02 16:41:40 -07:00
Michael GoinandClaude Opus 4.7 4f7309fcc0 [CI] Add ci-fetch-log.sh helper for Buildkite job logs (#41517) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 15:23:59 -07:00
Michael Goin 0a9362d6ab Revert "[Build] Make bundled DeepGEMM wheel portable across Python versions" (#41512) 2026-05-02 09:42:41 -07:00
Michael GoinandClaude cfd2573f23 [Build] Switch CUDA 13.0 wheel builds to PyTorch manylinux_2_28 base (#41416) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-05-02 05:51:28 -07:00
Hoang NguyenClaudemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Isotr0py
 		c3ad791e1a [Bugfix][Gemma 4] Clamp soft-token estimate to max_soft_tokens (#40796) 
Signed-off-by: Hoang Nguyen <118159510+hnt2601@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-05-02 06:34:59 +00:00
Matthew Santiago 8586369f61 Refactor Step3Text loading to use AutoWeightsLoader (#41492) 
Signed-off-by: Matthew Santiago <carag.matthew@gmail.com>
 2026-05-02 06:22:14 +00:00
Chauncey ae3b4deb8a [Doc] Add Codex usage example (#41358) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-05-01 22:27:43 -07:00
Rita Brugarolas c293ccc58e [ROCm][Bugfix] Fix init-time bias dtype cast when gate.out_dtype is None (#41405) 
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com>
 2026-05-02 00:13:15 -04:00
Luka Govedič d58c42e19c [vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2026-05-01 23:41:15 -04:00
Ekagra Ranjan 3e49479c4b Limit concurrency on test_transcription_api_correctness.py (#41478) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
 2026-05-02 03:19:07 +00:00
John Calderon 964a4bc2a5 [MM][CG] Support ViT CG for Qwen2.5-VL (#40830) 
Signed-off-by: John Calderon <jcalderon@nvidia.com>
 2026-05-02 11:10:14 +08:00
FredericOdermatt c408fdd663 [Fix] Sync gemma4 chat template from hf (#39570) 
Signed-off-by: Frederic Odermatt <frederic.odermatt@44ai.ch>
 2026-05-02 03:06:54 +00:00
Andy Lo 5737770c6c Re-enable allreduce rms fusion for DP / PP (#41458) 
Signed-off-by: Andy Lo <andy@mistral.ai>
 2026-05-01 19:01:37 -04:00
Michael Goin 0c99629ede [Build] Make bundled DeepGEMM wheel portable across Python versions (#41476) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-05-01 14:45:03 -07:00
Yongye Zhu edd60ac93a [Bugfix] Fix persistent_topk inter-CTA init race on RadixRowState (#41444) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
 2026-05-01 14:42:52 -07:00
Yongye Zhu bcf5cac9fb [DSV4] Add knob to enable pre-attn gemm (#41443) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
 2026-05-01 12:23:17 -07:00
Isotr0pyandRoger Wang a9484dac7b [Perf] Intergrate Tile Kernels head_compute_mix_kernel for Deepseek-V4 (#41255) 
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2026-05-01 15:01:17 -04:00
Matthew BonanniMichael GoinLucas Wilkinsonmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		f3fef12350 [Attention] Abstract the MLA prefill backends and eliminate cuDNN (#32623) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-05-01 13:36:20 -04:00
Wentao YeandNick Hill 51295793a2 [Model Runner V2] Add logprob_token_ids support (#40559) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-05-01 10:02:03 -07:00
Michael Goin 3ccc1ff495 [Eval][CI] Add basic mrcr eval to tests/evals/ (#40164) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-05-01 12:00:38 -04:00
vllmellmRita Brugarolasjunkang1991Luka GovedičTJian
 		529c671e80 [ROCm][FEAT] AITER Fused Allreduce + RMSNorm (#37646) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com>
Signed-off-by: junkang1991 <junkangchow@gmail.com>
Co-authored-by: Rita Brugarolas <Rita.BrugarolasBrufau@amd.com>
Co-authored-by: junkang1991 <junkangchow@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2026-05-01 23:07:18 +08:00
PleaplusoneandMatthew Wong bc635fad23 [ROCm][Deepseek] dsv3.2 further optimization (#41217) 
Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
 2026-05-01 23:06:00 +09:00
Artem Perevedentsevandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> c3e64696cd [Perf] Warmup forward_native sampler kernel (#41375) 
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-05-01 18:04:11 +04:00
sungsoo ha 4f7bde572a [Kernel] Pack output and LSE in DCP A2A (#41160) 2026-05-01 09:01:17 -04:00
Or Ozeri 2fa1f8ec00 [kv_offload+HMA][13/N]: Enable HMA support (#41445) 
This is the final PR in a series to enables HMA support for the
offloading connector. The connector advertises `SupportsHMA`
and is validated with unit tests and e2e tests.

Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-05-01 12:30:03 +01:00
raviguptaamd 7075df79b3 [ROCm] Enable DBO (Dynamic Batch Optimization) on ROCm (#34726) 
Signed-off-by: raviguptaamd <ravi.gupta@amd.com>
 2026-05-01 09:18:30 +00:00
Yuyi Ao 0dbaf9daad Refractor longcat loading to use AutoWeightsLoader (#41448) 
Signed-off-by: George-ao <yuyiao772@gmail.com>
 2026-05-01 09:07:23 +00:00
Seiji EicherMarwan SarieddineClaude
 		a3ec4a35f5 [Bugfix][Metrics] Fix RayPrometheusMetric.labels() returning shared labeled child (#40840) 
When vLLM runs with Ray Prometheus `vllm:request_success{finished_reason=...}`
only ever increments the repetition bucket regardless of the request's actual finish
reason; stop, length, abort, and error stay at zero. Root cause was `labels()` mutated
the wrapped Ray metric's default tags in place and returned self, so every `.labels(...)`
call on a given wrapper returned the same object. 

Co-authored-by: Marwan Sarieddine <sarieddine.marwan@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Signed-off-by: Marwan Sarieddine <sarieddine.marwan@gmail.com>
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
 2026-05-01 08:43:39 +01:00
Andreas Karatzas 32964e7700 [ROCm][CI] Upgraded UCX and RIXL (#41210) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-05-01 16:40:47 +09:00
Bugen Zhaoandwang.yuqi a07642667d [Bugfix] Pass reasoning parser kwargs to structured output (#41199) 
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
 2026-04-30 23:38:02 -07:00
baonudesifeizhai c3868bbbe4 [compile] Add FlashInfer FP8 async TP fusion and preserve allreduce fusion ordering #27893 (#39505) 
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
 2026-05-01 05:08:34 +00:00
sychen52 947138b6c2 Add nvfp4 kv cache support (#40177) 
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
 2026-05-01 04:55:16 +00:00
Or Ozeri 941fb50835 [kv_offload+HMA][12/N]: Scheduler-side support for sliding window groups (#41228) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-05-01 06:59:17 +03:00
Juhi Mittalandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 6b6ac6c3c7 [Kernel][MoE] Support GELU on TRT-LLM NvFP4 fused MoE for Gemma4 (#41050) 
Signed-off-by: Juhi Mittal <juhim@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-05-01 03:37:43 +00:00
Stefano Castagnetta b542bdf7fb [Bugfix] Disable FlashInfer CUTLASS MoE on SM110 (Jetson Thor AGX) (#40808) 
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
 2026-04-30 20:08:49 -07:00
Ronen Schaffer 415a879899 [KV Offload] Use Collection instead of Sequence/Iterable for OffloadingManager key parameters (#41361) 
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
 2026-05-01 05:18:38 +03:00
Dong W 7198940b39 [Model] Add Moondream3 model support(only query and caption skills) (#32325) 
Signed-off-by: Dong Wang <dongw2019@gmail.com>
 2026-05-01 10:06:48 +08:00
Luis 🚀andAndrew Sansom 14043dfecd feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720) 
Signed-off-by: Luis Robaina <luis@protopia.ai>
Signed-off-by: Luis Robaina 🚀 <luisfabian1545@gmail.com>
Signed-off-by: LuisRobaina <luis@protopia.ai>
Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
 2026-05-01 10:05:55 +08:00
Andreas Karatzas 1adaa5056b [ROCm][CI] Add ROCm score absolute tolerance floor (#41341) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-04-30 18:59:35 -07:00
SoyaazzandMatthew Bonanni 4d5c89295b (bugfix): block_size check for flex attn (#41363) 
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-04-30 18:59:26 -07:00
Nick Hill dd5506a157 [Core] Simplify handling of scheduler_reserve_full_isl option (#41064) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-04-30 18:10:00 -07:00
Yongye ZhuandRoger Wang a3c83ff2fd Faster per-token fp8 group quant packed kernel for blackwell (#41326) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2026-04-30 18:09:55 -07:00
Woosuk Kwon 9c61864bf8 [DeepSeek] Use torch.mm for bf16xbf16->fp32 gemm (#41300) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-04-30 16:28:57 -07:00
Tran Le 71725f6730 [Bugfix] Fix RoutedExpertsCapturer for Gemma 4 MoE (top_k_experts) (#41401) 
Signed-off-by: Tran Le <tranle@fireworks.ai>
 2026-04-30 16:19:59 -07:00
Yongye ZhuZijing LiuClaude Opus 4.7
 		b4806c8ee1 [DSV4] Add BF16 and MXFP8 A2A support for flashinfer a2a one sided (#40960) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Co-authored-by: Zijing Liu <liuzijing2014@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-30 15:33:12 -07:00
Wentao Ye 526927be94 [Model Runner v2] Fix v2 compile counter num_gpu_runner_capture_triggers and num_cudagraph_captured (#41285) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-04-30 15:20:11 -07:00
Michael Goin 75a4c166f2 Fix typo in log message for indexer cache (#41419) 
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2026-04-30 15:02:14 -07:00
fxmarty-amdandClaude 2917d6363a [NVFP4][Hopper/AMD Instinct] Add Triton kernels for NVFP4 dequantization and QDQ emulation (#40033) 
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-04-30 17:35:48 -04:00
Stefano Castagnetta efb4cdf2b8 [CI/Build] Skip Prithvi/Terratorch model-registry tests when terratorch is missing (#41389) 
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
 2026-04-30 12:47:55 -07:00