dbb7fffddb
[ROCm][MLA][DCP] Support causal multi-token verification ( #51705 )
...
Signed-off-by: Yichao Zhu <Yichao.Zhu@amd.com >
Signed-off-by: billishyahao <bill.he@amd.com >
Co-authored-by: andyluo7 <andy.luo@amd.com >
Co-authored-by: billishyahao <bill.he@amd.com >
2026-08-31 10:42:28 -07:00
Artem Perevedentsev
39e276eaeb
[Structured Output] Let terminal grammars stop under min_tokens (II) ( #54218 )
...
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com >
2026-08-31 20:39:27 +04:00
Nicolò Lucchesi
e9dd6d4834
[CI] Exclude kv_transfer changes from broad spec-decode/kernels/multimodal triggers ( #54365 )
...
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai >
2026-08-31 09:17:12 -07:00
rasmith and Andreas Karatzas
3593c964de
[ROCm] Add TheRock preview docker updates, Keep Python 3.12 and Ubuntu 22.04 ( #49925 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-31 11:09:46 -05:00
Fanli Lin and Kunshang Ji
82936c409d
[Tests][XPU] Limit Qwen2-VL generation length to avoid flaky numerical divergence ( #54172 )
...
Signed-off-by: Lin, Fanli <fanli.lin@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-08-31 22:59:57 +08:00
Zhenzhong Xu and Kunshang Ji
bd575a0d0b
[AutoRound] Support AutoRound Format Block-Wise FP8 in vLLM ( #47434 )
...
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com >
Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-08-31 22:56:20 +08:00
Nicolò Lucchesi
dafbef15a1
[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management ( #49445 )
...
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai >
2026-08-31 14:26:49 +00:00
andyluo7 and OpenAI Codex
76ff0cdff2
[Bugfix][ROCm] Preserve AITER unified-attention metadata during graph replay ( #53821 )
...
Signed-off-by: andyluo7 <andy.luo@amd.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-31 21:53:12 +08:00
c5d840ff6a
[KV Connector][Offloading] Certify attention-only hybrids in the canonical portability gate ( #51689 )
...
Signed-off-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-31 15:53:19 +03:00
4c58a0c398
[Bugfix][KV Offload] Unlink /dev/shm region after all workers map it (barrier variant of #51317 ) ( #52596 )
...
Signed-off-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai >
2026-08-31 15:53:00 +03:00
Uttam Kumar and Or Ozeri
e0d27040dd
[Bugfix][KV Offload][P2P] Preserve aborted loads until abort completion ( #52571 )
...
Signed-off-by: Uttam Kumar <uttam.kumar912@gmail.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-31 14:34:48 +03:00
Jee Jee Li
e2c8eeac40
[kernel] Fused embedding kernel ( #53677 )
...
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai >
2026-08-31 11:34:14 +00:00
bed3280f50
[KV offload] Order CPU->GPU loads against the compute stream ( #50696 )
...
Signed-off-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-31 14:31:18 +03:00
waizuichougou
810bc3250c
[Frontend][Performance] Resolve async media across modalities concurrently ( #54537 )
...
Signed-off-by: waizuichougou <2082431897@qq.com >
2026-08-31 10:50:17 +00:00
maithilijoshi20
9debcd5990
[Test][Qwen3-VL] Cover compiled DeepStack input contract ( #53529 )
...
Signed-off-by: maithilijoshi20 <97733343+maithilijoshi20@users.noreply.github.com >
2026-08-31 10:46:50 +00:00
Moein Khazraee
9acbc5360a
[KV Offload] Preserve KV event metadata until final residency removal ( #52068 )
...
Signed-off-by: Moein Khazraee <moein@nvidia.com >
2026-08-31 13:28:30 +03:00
wang.yuqi and Cyrus Leung
eeb549a74d
[Frontend] Move engine/protocol.py out openai folder ( #54492 )
...
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 >
2026-08-31 10:13:50 +00:00
liranschour
d8de4ae322
[Bugfix][KVOffload] P2P tier declares REQUEST_LEVEL on the producer leg ( #52912 )
...
Signed-off-by: Liran Schour <lirans@il.ibm.com >
2026-08-31 10:07:20 +00:00
699e180df4
[Bugfix][SM120] DSv4: pass contiguous C128A decode topk indices on SM120 ( #53574 )
...
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-31 09:44:42 +00:00
Hotragn Pettugani
28bf75c9a9
[Bugfix][Frontend] Truncate prompt_is_token_ids with the prompt ( #54509 )
...
Signed-off-by: hotragn <hotragn.pettugani_2024@woxsen.edu.in >
2026-08-31 09:29:01 +00:00
Andreas Karatzas
399247cc88
[Bugfix][MM] Fix MiniCPM-o image processor reuse on Transformers v5 ( #54501 )
...
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com >
2026-08-31 17:07:52 +08:00
wang.yuqi
5bfd76372d
[Renderer] Shutdown the renderer properly. ( #52124 )
...
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io >
2026-08-31 08:40:37 +00:00
jl9876 and Kunshang Ji
1b9539d37c
[Quantization][Autoround][XPU] Support AutoRound MXFP8 MoE models ( #51248 )
...
Signed-off-by: jl9876 <jia.li@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-08-31 16:37:01 +08:00
Tianmu Li and OpenAI Codex
c6c33f2b1f
[CPU] Support FP16/BF16 persisted GDN state on AMX ( #52191 )
...
Signed-off-by: Li, Tianmu <tianmu.li@intel.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-31 16:32:20 +08:00
zofia and opencode
2a61f060d3
[XPU] Ensure unquantized linear weight is N-contiguous ( #53536 )
...
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com >
Co-authored-by: opencode <noreply@opencode.ai >
2026-08-31 16:01:24 +08:00
Li, Jiang
fdbf2ddbd2
[Bugfix][CPU] Fix several bugs ( #54042 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com >
2026-08-31 15:33:06 +08:00
2cf82bcdd1
[Bugfix][DCP] Fix NVIDIA DeepSeek-V3.2 / GLM-5.2 fused attention ( #50005 )
...
Signed-off-by: 云挚 <ningyunxiao.nyx@antgroup.com >
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net >
Co-authored-by: Mikhail Kostryukov <mike@triptrack.net >
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com >
2026-08-31 00:30:45 -07:00
f9d666f917
[KV Offload] Forward ownership in KV cache events ( #52067 )
...
Signed-off-by: Moein Khazraee <moein@nvidia.com >
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2026-08-31 10:28:41 +03:00
Jee Jee Li
8e92248f79
[Kernel] Retire the DSv3 router GEMM CUDA kernel ( #54040 )
...
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai >
2026-08-31 07:15:31 +00:00
da0b2d8b17
[Performance] Optimize Dots3 NOTE runtime ( #53517 )
...
Signed-off-by: KurodaKanbei <mistergalahad@gmail.com >
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai >
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai >
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com >
2026-08-31 00:05:18 -07:00
Prudhvi Vuda
7292ee2791
[Bugfix][Multimodal] Honor modality-scoped mm_processor_kwargs ( #53808 )
...
Signed-off-by: Prudhvivuda <prudhvi12042001@gmail.com >
2026-08-31 06:37:12 +00:00
eligotts and OpenAI Codex
4ae172231c
[Frontend] Forward cache salt for content parts ( #54315 )
...
Signed-off-by: Eli Gotts <78387377+eligotts@users.noreply.github.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-30 23:29:53 -07:00
Hotragn Pettugani
8fd9eb85d5
[Bugfix][Frontend] Truncate prompt_token_offsets with the prompt ( #54407 )
...
Signed-off-by: hotragn <hotragn.pettugani_2024@woxsen.edu.in >
2026-08-31 06:13:37 +00:00
+5
e126687a9a
[Model] Support Qwen3.8-Flash-Next ( #53896 )
...
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com >
Signed-off-by: andyluo7 <andy.luo@amd.com >
Signed-off-by: lishunyang12 <lishunyang03@gmail.com >
Signed-off-by: Harry Huang <huanghaoyan.hhy@alibaba-inc.com >
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg >
Signed-off-by: Isotr0py <Isotr0py@outlook.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai >
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: KungYork <firelikest@163.com >
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg >
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai >
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com >
Co-authored-by: Isotr0py <mozf@inferact.ai >
Co-authored-by: andyluo7 <andy.luo@amd.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
Co-authored-by: lishunyang12 <lishunyang03@gmail.com >
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com >
Co-authored-by: Isotr0py <Isotr0py@outlook.com >
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-31 05:57:56 +00:00
Hotragn Pettugani
687db59744
[Bugfix][Frontend] Truncate pooling prompts before padding them ( #54364 )
...
Signed-off-by: hotragn <hotragn.pettugani_2024@woxsen.edu.in >
2026-08-30 22:12:03 -07:00
LironKesem
44fe2a392b
[CPU] add CPU support for Voxtral ( #53921 )
...
Signed-off-by: Liron Kesem <52330564+LironKesem@users.noreply.github.com >
2026-08-31 04:20:37 +00:00
Jee Jee Li
648b7468b8
[CI/Build] Fix Kimi K3 Eagle3 test fixture ( #54482 )
...
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai >
2026-08-31 03:29:45 +00:00
Isotr0py
555ea65e8c
[Frontend] Add video embeds input support ( #54242 )
...
Signed-off-by: Isotr0py <Isotr0py@outlook.com >
2026-08-31 03:20:47 +00:00
Lucas Wilkinson
5707355209
[Bugfix][MLA] Fix BLHNC addressing for FlashInfer sparse MLA ( #54465 )
...
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
2026-08-31 01:13:42 +00:00
AI-Infra Rookie
c92b29a1d4
[Bugfix] Make metadata send non-blocking in GroupCoordinator.isend_tensor_dict ( #49274 )
...
Signed-off-by: z00897177 <zhouxinyi6@huawei.com >
2026-08-30 23:51:25 +00:00
7ab2923489
[Flashinfer] Upgrade Flashinfer version to 0.6.18 ( #54313 )
...
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com >
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com >
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com >
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com >
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com >
2026-08-30 16:01:05 -07:00
Kevin H. Luu
7a100bb617
[CI] Restore gpu_1_queue routing for torch-abi audit ( #54468 )
...
Signed-off-by: khluu <khluu000@gmail.com >
2026-08-30 14:59:36 -07:00
Kevin H. Luu
b2dc864bb6
[Bugfix][Spec Decode] Keep default CUDA graph sizes memory-safe ( #54418 )
...
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com >
2026-08-30 18:02:31 +00:00
Aditya Jha and Claude
9d0fe9bac8
[Bugfix][Quantization][MoE] Route weight only NVFP4 checkpoints through W4A16 ( #54427 )
...
Signed-off-by: Aditya Jha <4adityajha@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-08-30 13:02:15 -04:00
Juan Pérez de Algaba
e79961c946
[codeowners] Add jperezdealgaba to security file ownership ( #54358 )
...
Adds Juan Pérez de Algaba (`@jperezdealgaba`) alongside Russell Bryant as a CODEOWNER for the vLLM security guide, security policy, and vulnerability-management documentation.
2026-08-30 16:24:21 +00:00
waizuichougou and OpenAI Codex
f6895a5fcb
[Bugfix][Multimodal] Avoid caching full prompts in fallback ( #54439 )
...
Signed-off-by: waizuichougou <2082431897@qq.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-30 16:19:38 +00:00
56058fd572
[Bugfix][Kernel] Keep packed GDN decode beta in FP32 ( #53877 )
...
Signed-off-by: CherryLemon <lemon_cn@alumni.sjtu.edu.cn >
Co-authored-by: Codex <codex@openai.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com >
2026-08-30 22:15:36 +08:00
machero and Claude
87b9b5b8d9
[Test][VLM] Add batch-invariance tests for Qwen3-VL ( #53531 )
...
Signed-off-by: machero <sr1123640465@126.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-08-30 09:49:41 -04:00
Taneem Ibrahim
fe6db3ed5e
[Bugfix] Validate scale-out transfer params ( #54324 )
...
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com >
2026-08-30 09:46:12 -04:00
Harry Mellor and Claude Opus 5
488b6da105
[Doc] Fix griffe warnings in HYV4 tool parser ( #54412 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-08-30 13:21:22 +00:00
