5 Commits

Author SHA1 Message Date
Michael Goin
0852527647
[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2025-11-07 18:20:55 -08:00
Ming Yang
527821d191
Use macro guard CUDA functions for back compatibility in grouped_topk_kernel.cu (#25346)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
2025-09-23 09:45:39 -07:00
Lumina
81b16a2bc9
[Kernel] Better inf handling for grouped topk cu (#24886)
Signed-off-by: lumina37 <starry.qvq@gmail.com>
2025-09-18 05:53:55 +00:00
Qiming Zhang
e919d6f549
[Kernel][Bugfix] Fix grouped topk cu (#24146)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
2025-09-04 12:37:37 +08:00
Xin Yang
8a3cd90af5
[Kernel] Add fused grouped_topk kernel for MoE (#23274)
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2025-08-25 11:47:52 -07:00