|
4eafc72928
|
[Audio] Bundle get_generation_prompt() params into SpeechToTextParams (#36268)
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2026-04-22 12:24:18 +08:00 |
|
|
Micah Williamson
|
6d09769700
|
[ROCm] Support non-causal attention in ROCM_ATTN (#40176)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-04-22 12:57:12 +09:00 |
|
|
Carl Yandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
4506319a28
|
[compile] mla + group fp8 fusion (#38877)
Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-21 23:16:58 -04:00 |
|
|
Rishapveer Singhandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9b60e2ffaa
|
[Bugfix] Fix quantized model initialization failure with prefetch offloading (#40432)
Signed-off-by: Rishapveer Singh <singhrishapveer@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-21 20:15:58 -07:00 |
|
|
Martin Hickey
|
3951d3eacd
|
[MyPy] Enable mypy for vllm/model_executor/layers/ (#40159)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-04-21 20:15:02 -07:00 |
|
|
|
6f2c71be8f
|
[Multimodal] Add PyAV video backend for concurrent video decoding (#39986)
Signed-off-by: Jaseel Muhammad <jaseel.muhammad@mbzuai.ac.ae>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-04-21 20:14:57 -07:00 |
|
|
rasmith
|
2463f00fb6
|
[AMD][CI][BugFix] Override normalize_e4m3fn_to_e4m3fnuz for fnuz machines in test_moe_layer_no_parallel (#40550)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2026-04-22 02:21:02 +00:00 |
|
|
|
f946659fff
|
[Bugfix] Fix W4A8_FP8 MoE tp>1 correctness and view() TypeError (#40310)
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-21 21:58:33 -04:00 |
|
|
Soila Kavulya
|
f90aa44662
|
[NIXL][XPU]Fix nixl import on XPU (#40430)
Signed-off-by: Soila Kavulya <soila.p.kavulya.intel.com>
|
2026-04-22 09:26:33 +08:00 |
|
|
rasmith
|
cefa5281a7
|
[ROCm][P/D][MORI][BugFix] Ensure correct api is used when making requests to prefill / decode nodes (#39835)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2026-04-22 09:48:25 +09:00 |
|
|
Jhao-Ting Chen
|
46794958f0
|
test: add nan/inf clamp regression test for fused_topk_bias (#40553)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
|
2026-04-22 00:46:53 +00:00 |
|
|
Khushali Desai
|
6ff8dea075
|
[Bugfix] avoid warmup if text only expectation in multi_modal run (#40409)
Signed-off-by: khushali9 <khushali.desai9@gmail.com>
|
2026-04-22 00:19:50 +00:00 |
|
|
TJian
|
583e6f2226
|
[ROCm] [Wheel] [Bugfix] [Critical] Remove any packages installed from github from rocm.txt e.g fastsafetensors as it is incompatible with uv pip (#40461)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-04-22 00:18:07 +00:00 |
|
|
Matthew BonanniandTyler Michael Smith
|
96a85c5750
|
[Startup][UX] Enable CUDAGraph memory profiling by default (#38284)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-04-21 18:16:59 -04:00 |
|
|
bnellnmandRobert Shaw
|
9db4650e5e
|
[MoE Refactor] Add more MoE layer tests (#39349)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-04-21 18:12:36 -04:00 |
|
|
bnellnm
|
5e584ce9ec
|
[MoE Refactor] Remove SharedFusedMoE class (#35782)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-04-21 18:12:12 -04:00 |
|
|
Wentao Ye
|
1842447c09
|
[Refactor] Remove unused param (#39750)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-04-21 14:59:20 -07:00 |
|
|
Wentao Ye
|
16688b26a6
|
[Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-04-21 19:51:03 +00:00 |
|
|
Jakub Zakrzewski
|
6fbec8ed47
|
[Bugfix][Kernel] nvfp4 cutlass MoE: fix nvfp4 experts quant out-of-bounds read for expert counts not divisible by 4 or 16 (#40351)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
|
2026-04-21 19:06:09 +00:00 |
|
|
FergusandChauncey
|
5544f8c18b
|
[Performance] Add is_reasoning_end_streaming() override to GptOssReasoningParser (#35745)
Signed-off-by: Fergus <fergus.barratt00@gmail.com>
Signed-off-by: fergus barratt <fergus.barratt00@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-04-21 18:31:27 +00:00 |
|
|
|
9f39b380d0
|
[Bugfix] Fix spec decode test failures on Blackwell (SM100+) (#39546)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Signed-off-by: Rishi Puri <puririshi98@berkeley.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-04-21 18:21:19 +00:00 |
|
|
Zijing Liu
|
9a6a66f3b8
|
[MRv2]fix: model accuracy regression caused by reusing the stale last_sampled_tokens and draft_tokens (#39833)
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
|
2026-04-21 16:30:32 +00:00 |
|
|
Isotr0pyandRoger Wang
|
67eb6083e3
|
Revert "[Misc] Move pyav and soundfile to common requirements" (#40276)
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-04-21 09:08:06 -07:00 |
|
|
Harry Mellor
|
6ee081d1d0
|
Add new tp plan styles to the Transformers modelling backend (#40467)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-04-21 08:51:30 -07:00 |
|
|
Wentao YeandNick Hill
|
66cc3fa559
|
[Model Runner V2] Multiple prompt logprobs support (#39937)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-04-21 15:49:05 +00:00 |
|
|
Vadim Gimpelson
|
6d85b36a9f
|
Revert #38730 and #38791 (#40032)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-04-21 11:44:11 -04:00 |
|
|
Matthew Bonanni
|
ab5666eb7c
|
[UX] Bump version in CG memory profiling log message (#40465)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-04-21 15:26:06 +00:00 |
|
|
roikoren755
|
f819265a4a
|
Default to 'align' mamba cache mode for Mamba-based models when speculative decoding is enabled (#40454)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-04-21 14:51:43 +00:00 |
|
|
Shanshan Shen
|
936e0b79aa
|
[MM][CG] Optimize default max_frames_per_batch auto-infer for ViT CUDA graph video inference (#40445)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-04-21 14:47:53 +00:00 |
|
|
xiangdongandKunshang Ji
|
b2a5518679
|
[XPU][CI] Add misc, engine and lora cases on Intel GPU in CI (#39887)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-04-21 22:30:46 +08:00 |
|
|
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
|
908a713488
|
[Bugfix] LoRA: extend expert base_layer loading to Qwen3.5 and Step3.x (#37114)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
|
2026-04-21 14:17:03 +00:00 |
|
|
Yusuf Mohammadandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ec5ef0ac73
|
[Doc] Add Qwen3 AWQ models to documentation (#40034)
Signed-off-by: Yusuf <yusufmohammad@live.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-21 09:37:41 -04:00 |
|
|
Talor Abramovichandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
7b1e0b07d0
|
[Bugfix] Fix dataset name and path argument validation bug in vllm bench serve (#40288)
Signed-off-by: talora <talora@nvidia.com>
Signed-off-by: Talor Abramovich <talor19@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-04-21 06:14:28 -07:00 |
|
|
|
d249a9e90e
|
Add Granite 4.1 Vision as built-in multimodal model (#40282)
Signed-off-by: Artem Spector <artems@il.ibm.com>
Signed-off-by: artemspector <artems@il.ibm.com>
Co-authored-by: artemspector <artems@il.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-04-21 05:43:39 -07:00 |
|
|
|
d2e2e856ad
|
[Frontend] Remove frontend pooling multi task support. (#37861)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-21 12:27:44 +00:00 |
|
|
Kris HungandClaude Opus 4.6
|
766cb65d00
|
feat(multimodal): support externally processed mm_kwargs with cache injection (#39502)
Signed-off-by: Krish Hung <krishung5@gmail.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-21 11:31:09 +00:00 |
|
|
Jhao-Ting Chen
|
28c222157b
|
fix: clamp NaN/Inf in topk_softmax to prevent duplicate expert IDs (#39391)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
|
2026-04-21 15:04:41 +04:00 |
|
|
wang.yuqi
|
3975eb6de6
|
Revert "[Startup] Parallelize torch/transformers import + weight prefetch + forkserver prewarm" (#40438)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-04-21 08:47:18 +00:00 |
|
|
Zeyu Zhang
|
5a94a19824
|
[Bugfix] Normalize malformed dict prompts that carry token IDs in prompt (#40339)
Signed-off-by: Alchuang22-dev <2584829494@qq.com>
|
2026-04-21 07:44:36 +00:00 |
|
|
hangy-amd
|
f95c11a848
|
[Feat] dflash support for ROCm (#39703)
Signed-off-by: Hang Yang <hangy@amd.com>
|
2026-04-21 14:58:20 +08:00 |
|
|
milesial
|
257015d5e5
|
[MoE] Triton MoE Perf regression - restore low latency path (#39016)
|
2026-04-21 02:37:11 -04:00 |
|
|
Shanshan Shen
|
b47840019e
|
[MM][Misc] Support image+video mixed inputs (per prompt) for VLM examples (#40335)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-04-21 03:43:25 +00:00 |
|
|
SeongJun Lee
|
989cc12d88
|
[Fix] Add missing space in IP fallback warning (#40359)
Signed-off-by: lesj0610 <lesj0610@gmail.com>
|
2026-04-20 20:26:06 -07:00 |
|
|
Wentao Ye
|
301024aa9c
|
[Deprecation] Deprecate cprofile and cprofile_context (#39100)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-04-21 11:25:22 +08:00 |
|
|
Simon Mo
|
8256833fe6
|
[Startup] Parallelize torch/transformers import + weight prefetch + forkserver prewarm (#40331)
Signed-off-by: simon-mo <simon@inferact.ai>
|
2026-04-21 10:49:32 +08:00 |
|
|
Shanshan Shen
|
8097591286
|
[Doc] Update ViT CUDA graph doc for mixed (image+video) inputs (#40355)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-04-21 02:31:09 +00:00 |
|
|
Luciano MartinsandLuciano Martins
|
20d3743491
|
[Bugfix] Gemma4: fix multimodal embedder norm order to match HF reference (#40411)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-04-21 02:28:26 +00:00 |
|
|
Chauncey
|
18563f2072
|
[Misc] Reduce attention logging levels (#40086)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-04-21 02:09:25 +00:00 |
|
|
MisaandMisael Casarez
|
0e884fe638
|
[Bugfix] Fix _CONFIG_REGISTRY types getting wrong config class when on-disk model_type differs (#39554)
Signed-off-by: Misa <misaAle@users.noreply.github.com>
Signed-off-by: Misael Casarez <misacasa@amazon.com>
Co-authored-by: Misael Casarez <misacasa@amazon.com>
|
2026-04-20 19:04:48 -07:00 |
|
|
|
fe5c115ee4
|
[vLLM IR] Add IR op testing and benchmarking infrastructure (#40167)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Theresa Shan <Theresa.Shan@amd.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-21 00:23:03 +00:00 |
|