- 07 Nov, 2025 1 commit
-
-
smit kadvani authored
Signed-off-by:
Smit Kadvani <smit.kadvani@gmail.com> Co-authored-by:
Smit Shaileshbhai Kadvani <kadvani@meta.com>
-
- 06 Nov, 2025 7 commits
-
-
Aleksandr Malyshev authored
Signed-off-by:
Aleksandr Malyshev <maleksan@amd.com> Co-authored-by:
Aleksandr Malyshev <maleksan@amd.com> Co-authored-by:
Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
-
Julien Denize authored
Signed-off-by:Julien Denize <julien.denize@mistral.ai>
-
Eric Yue authored
Signed-off-by:minatoaquaMK2 <jiacheng.yue@foxmail.com>
-
xiangze-arm authored
Signed-off-by:Zhang Xiangze <Xiangze.Zhang@arm.com>
-
Xiaozhu Meng authored
Signed-off-by:Xiaozhu <mxz297@gmail.com>
-
Wentao Ye authored
[Feature] Enable TP + EP `shared_experts` overlap with router, 3.7% E2E performance improvement (#28164) Signed-off-by:yewentao256 <zhyanwentao@126.com>
-
Vadim Gimpelson authored
Signed-off-by:Vadim Gimpelson <vadim.gimpelson@gmail.com>
-
- 05 Nov, 2025 5 commits
-
-
Paul Zhang authored
Signed-off-by:PaulZhang12 <paulzhan@fb.com>
-
Frost Mitchell authored
Signed-off-by:frost-intel <frost.mitchell@intel.com>
-
amirkl94 authored
Signed-off-by:
Amir Klein <203507526+amirkl94@users.noreply.github.com> Co-authored-by:
Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by:
Michael Goin <mgoin64@gmail.com>
-
Kunshang Ji authored
Signed-off-by:Kunshang Ji <kunshang.ji@intel.com>
-
tou authored
-
- 04 Nov, 2025 9 commits
-
-
Vadim Gimpelson authored
Signed-off-by:Vadim Gimpelson <vadim.gimpelson@gmail.com>
-
Aleksandr Malyshev authored
Signed-off-by:
Aleksandr Malyshev <maleksan@amd.com> Co-authored-by:
Aleksandr Malyshev <maleksan@amd.com>
-
Vadim Gimpelson authored
Signed-off-by:Vadim Gimpelson <vadim.gimpelson@gmail.com>
-
bnellnm authored
-
tomeras91 authored
Signed-off-by:Tomer Asida <57313761+tomeras91@users.noreply.github.com>
-
Jerry Zhang authored
Signed-off-by:Jerry Zhang <jerryzh168@gmail.com>
-
Varun Sundar Rabindranath authored
-
Wentao Ye authored
[Bug] Batch invariant: Fix flash attn MLA `RuntimeError: scheduler_metadata must have shape (metadata_size)` (#27884)
-
vllmellm authored
Signed-off-by:vllmellm <vllm.ellm@embeddedllm.com>
-
- 03 Nov, 2025 2 commits
-
-
Tyler Michael Smith authored
Signed-off-by:Tyler Michael Smith <tlrmchlsmth@gmail.com>
-
Hank_ authored
-
- 02 Nov, 2025 1 commit
-
-
Asaf Joseph Gardin authored
Signed-off-by:asafg <39553475+Josephasafg@users.noreply.github.com>
-
- 01 Nov, 2025 2 commits
-
-
Jee Jee Li authored
Signed-off-by:Jee Jee Li <pandaleefree@gmail.com>
-
Jee Jee Li authored
Signed-off-by:Jee Jee Li <pandaleefree@gmail.com>
-
- 31 Oct, 2025 2 commits
-
-
Shu Wang authored
Signed-off-by:Shu Wang. <shuw@nvidia.com>
-
Jiangyun Zhu authored
Signed-off-by:zjy0516 <riverclouds.zhu@qq.com>
-
- 30 Oct, 2025 7 commits
-
-
Paul Zhang authored
Signed-off-by:
PaulZhang12 <paulzhan@fb.com> Co-authored-by:
Wentao Ye <44945378+yewentao256@users.noreply.github.com>
-
Roger Meier authored
Signed-off-by:Roger Meier <r.meier@siemens.com>
-
Li, Jiang authored
Signed-off-by:jiang1.li <jiang1.li@intel.com>
-
Zhiyuan Li authored
Signed-off-by:
lizhiyuan <lizhiyuan@moonshot.cn> Signed-off-by:
Zhiyuan Li <uniartisan2017@gmail.com>
-
wang.yuqi authored
Signed-off-by:
wang.yuqi <noooop@126.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>
-
Bram Wasti authored
Signed-off-by:
Bram Wasti <bwasti@meta.com> Signed-off-by:
Bram Wasti <bwasti@fb.com> Co-authored-by:
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
-
Yan Ma authored
Signed-off-by:Yan Ma <yan.ma@intel.com>
-
- 29 Oct, 2025 4 commits
-
-
Wentao Ye authored
Signed-off-by:yewentao256 <zhyanwentao@126.com>
-
Wentao Ye authored
[Bug] Fix DeepEP low latency `assert self.batched_router_logits.size(-1) == full_router_logits.size(-1)` Bug (#27682) Signed-off-by:yewentao256 <zhyanwentao@126.com>
-
Roger Young authored
Signed-off-by:
xuebi <xuebi@minimaxi.com> Co-authored-by:
xuebi <xuebi@minimaxi.com>
-
Zhewen Li authored
Signed-off-by:zhewenli <zhewenli@meta.com>
-