 Oxana KorzhandClaude Opus 5
|
fb68025138
|
[Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-28 22:09:08 -07:00 |
|
|
|
b2f685834a
|
[Hy4] support Hy4-preview model (#54160)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: russellfeng <russellfeng@tencent.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-29 12:07:28 +08:00 |
|
|
Nick Hill
|
6c18a54648
|
[Perf] Avoid h2d copies from non-pinned CPU tensors (#54299)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-29 12:06:30 +08:00 |
|
|
kaiyuanxieandCalvinXKY
|
738bc8811a
|
[BugFix] Disable TP for Qwen3-Omni audio encoder when heads % TP != 0 (#50858)
Signed-off-by: CalvinXKY <xky@users.noreply.github.com>
Co-authored-by: CalvinXKY <xky@users.noreply.github.com>
|
2026-08-29 11:18:04 +08:00 |
|
|
|
46a83642f6
|
[Perf] Pin CPU tensors before non_blocking H2D in three MM paths (#54292)
Signed-off-by: Keyi Li <likey6688@gmail.com>
Co-authored-by: Keyi Li <likey6688@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
|
2026-08-28 20:13:40 -07:00 |
|
|
Ronaldandaoshen02
|
16d6c376bc
|
[Bugfix][Models] Register sleep-managed runtime buffers (#53507)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-08-29 10:32:24 +08:00 |
|
|
Shinichi Hemmi
|
df14152ac6
|
[Model] Support speculative decoding method for PLaMo3 (#54239)
Signed-off-by: Shinichi Hemmi <shemmi@preferred.jp>
|
2026-08-28 22:31:07 +00:00 |
|
|
|
c274d36103
|
[Bugfix] Keep the Moondream3 MoE all-reduce out of the fused-path try (#54152)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-08-28 15:06:42 -07:00 |
|
|
Nick HillandKimi Code
|
70732942c6
|
[Bugfix][ROCm] Pre-allocate wvSplitKrc static workspaces before KV init (#54247)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
|
2026-08-28 14:22:53 -07:00 |
|
|
Taneem IbrahimandWentao Ye
|
21fa2c5a2a
|
[Mypy] Fix mypy typing for model interfaces and H/I models (#54079)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-08-28 16:49:19 -04:00 |
|
|
afriedriandAndreas Karatzas
|
2f1cba799e
|
[ROCm] remove VLLM_ROCM_USE_AITER_FP4_ASM_GEMM environment variable; make w4a4 use the preshuffle triton+asm by default (#53141)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
Signed-off-by: afriedri <afriedri@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-28 18:59:53 +00:00 |
|
|
Chipmunk
|
ffe690eca9
|
[MM][CG] Support ViT full CUDA graph for Idefics3 and SmolVLM (#47625)
Signed-off-by: Ryouichi Kurihara <ryouichi.kurihara.628@gmail.com>
|
2026-08-28 17:16:31 +00:00 |
|
|
xuebwang-amd
|
06569a8696
|
[ROCm][Quantization][MOE] Enable fused shared experts for block-quantized FP8 (#53097)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
|
2026-08-28 09:23:07 -07:00 |
|
|
maobaolongandCodex
|
6f7df92a8e
|
[CPU][MLA] Fix prefill backend selection so MLA runs end-to-end on CPU (#51471)
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-28 12:36:55 +08:00 |
|
|
Thien Tran
|
6ec92bcbc8
|
[Kimi-K3] Merge MLA gate into QKV-A projection (#54015)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-08-27 17:47:18 -07:00 |
|
|
|
7c877062ac
|
[kernel] Integrate FlashInfer BF16 CuTeDSL Low Latency GEMM (#50572)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-27 22:29:12 +00:00 |
|
|
Matthew BonanniandOpenAI Codex
|
de9250ac9e
|
[Attention] Enable masked MHA for GLM-5 head dimensions (#53785)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-27 21:17:12 +00:00 |
|
|
Chauncey
|
7d5769b2d9
|
[Perf][DSv4] Use native CUDA SwiGLU clamp kernel for Humming MoE (throughput +1.40%) (#53685)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-08-27 13:52:45 -07:00 |
|
|
Elvir Crnčević
|
674c284dbd
|
Fix Humming MoE activation_output aliasing (#54056)
|
2026-08-27 18:28:38 +00:00 |
|
|
Khushali Desai
|
c7b0467c25
|
buffer size insuffient Dspark sd for FlashInfer MNNVL allreduce (#50932)
|
2026-08-27 11:01:08 -04:00 |
|
|
hcl
|
42e7942ac9
|
fix(config): guard LlamaBidirectionalConfig against missing hf_config.pooling (#50536)
Signed-off-by: Chenglun Hu <chenglunhu@gmail.com>
|
2026-08-27 18:56:07 +08:00 |
|
|
Luciano MartinsandLuciano Martins
|
2ab187430b
|
[Bugfix] Make Gemma4 MTP suppress_tokens masking CUDA-graph-safe (#53884)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-08-26 15:39:19 +00:00 |
|
|
Oliver HolworthyandOpenAI Codex
|
28b484e5d7
|
[Model] Pixtral: use packed multimodal encoder attention (#52185)
Signed-off-by: Oliver Holworthy <1216955+oliverholworthy@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-26 14:14:40 +00:00 |
|
|
|
c47ca4aaeb
|
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[tT]" (#53466)
Signed-off-by: Jensen Chen <a1043904820@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-26 14:12:11 +00:00 |
|
|
Robert ShawandRobert Shaw
|
6a5e8f5979
|
[DeepEPv2] Support MXFp8 Activation Scale Dispatch (#51398)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-08-26 12:26:11 +00:00 |
|
|
|
61d4f56635
|
[Offloader] Offload submodules that make_layers never reaches (#53120)
Signed-off-by: ray24777 <103923677+ray24777@users.noreply.github.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-26 18:37:00 +08:00 |
|
|
|
2267d3b112
|
[AttentionBackend][HPC-ops] update hpc rope norm to support stride kv cache (#53705)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-08-26 08:20:28 +00:00 |
|
|
Hung Hoang (黄兴）
|
a5f82882a6
|
[Bugfix][Model] Honor Molmo2 dummy video num_frames >= 2 override (#53830)
Signed-off-by: hungh <hungh@nvidia.com>
|
2026-08-26 06:47:02 +00:00 |
|
|
|
044b05220e
|
[Kernel][Perf] Tune fused_moe FP8 config for Qwen3.5 on L40S (+7%) (#53819)
Signed-off-by: nizhang1 <nizhang1@coupang.com>
Co-authored-by: nizhang1 <nizhang1@coupang.com>
Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
|
2026-08-26 04:02:26 +00:00 |
|
|
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
a5e0045433
|
[Refactor] Remove dead code quantization 2 (#52821)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-25 20:28:44 -07:00 |
|
|
linitra24
|
f6130145c8
|
[Bugfix][LoRA] Enable tower/connector LoRA for Qwen3-Omni (#53557)
Signed-off-by: linitra24 <Joy25810@foxmail.com>
|
2026-08-26 10:44:41 +08:00 |
|
|
Wentao Ye
|
384d079697
|
[Perf] Autotune batch invariance triton kernel in blackwell, 33.6% E2E latency reduction (#53649)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 15:06:01 -04:00 |
|
|
Wentao Ye
|
70021a0081
|
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[gG]" (#53616)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 09:47:16 -07:00 |
|
|
|
ca29cd48ba
|
[Quantization][Humming] Support MXFP4 weight + block-FP8 activation for MoE (#51332)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-25 10:21:00 -04:00 |
|
|
Jiatai WangandOpenAI Codex
|
06ecec7a84
|
[Bugfix][MM] Fix JinaVL processing cache order (#53553)
Signed-off-by: JiataiWang <wangjiatai@proton.me>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-25 00:03:05 -07:00 |
|
|
|
48d7132962
|
[Model] Migrate FlexOlmo, Olmo3 and Hunyuan V1/VL to the Transformers modeling backend (#53615)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-08-24 22:39:05 -07:00 |
|
|
Karan Shelar
|
a9a17e7095
|
Dflash2 load fix (#53435)
|
2026-08-24 21:32:43 -07:00 |
|
|
Harry MellorandClaude Opus 5
|
b2dd9ce73d
|
[Docs] Fix docstring continuation indentation in routed_experts.py (#53604)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-25 02:27:16 +00:00 |
|
|
Zupeng Wang
|
7b7e5cbfcd
|
[Bugfix][LoRA] Restore tower and connector LoRA support for LFM2-VL (#53519)
Signed-off-by: Zupeng Wang <71580390+zupengwang@users.noreply.github.com>
|
2026-08-25 01:53:04 +00:00 |
|
|
kiroxuandOpenAI Codex
|
07ef21bc69
|
[Kernel][Perf] Enable fused QK-norm + partial MRoPE + gate for Qwen3.6 (#52676)
Signed-off-by: kiroxu <148877251+BabyDrangoner@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-24 18:28:49 -07:00 |
|
|
Nick Hill
|
09fddeb4ce
|
[Bugfix] BailingMoeV3 KDA: skip absent metadata during CUDA graph profiling (#53593)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-25 01:02:50 +00:00 |
|
|
|
7ca336929c
|
[Model] Remove ten deprecated model architectures (#53608)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-24 17:06:00 -07:00 |
|
|
Giancarlo Delfin
|
d154d90d6c
|
[Model Runner V2] batch-sharded sample (#50465)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
|
2026-08-24 15:49:57 -07:00 |
|
|
Wentao Ye
|
f59bb0bd8c
|
[Refactor] Refactor batch invariance folder (#53619)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-24 14:31:36 -07:00 |
|
|
Prudhvi Vudaandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
342b8ebd8b
|
[Bugfix][Multimodal] Encode text in mixed CLIP/SigLIP pooling batches (#53165)
Signed-off-by: Prudhvivuda <prudhvi12042001@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-24 10:45:42 -07:00 |
|
|
Jee Jee LiandCyrus Leung
|
4f686e182a
|
[MISC] Cleanup deprecated parameters (#53559)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-08-24 10:19:04 -07:00 |
|
|
Ning Xie
|
6648eb118d
|
[Core] drop duplicate VLLM_USE_DEEP_GEMM check (#48687)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
|
2026-08-24 16:30:50 +00:00 |
|
|
Lio Einaudiandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
7797b6022c
|
[Kernel][Perf] Per-architecture tuned configs for batch-invariant persistent matmul (~3x decode kernels on RTX 4090D/H20) (#53247)
Signed-off-by: LioEinaudi <zhao3024667639@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-24 11:28:51 -04:00 |
|
|
Wentao Ye
|
29c9af5211
|
[Kimi K3 Refactor] Add UnfinalizedMoEOutput proto following up for #53152 (#53310)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-24 11:21:11 -04:00 |
|
|
cjackal
|
22099afc64
|
[Bugfix][DCP] Handle sparse MLA metadata after DCP Manager refactor (#52377)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
|
2026-08-24 15:02:48 +00:00 |
|