Commits · 8d75f22e79656dddc975c73133fdccbbebc5c963 · OpenDAS / vllm_cscc

"components/backends/trtllm/launch/disagg.sh" did not exist on "901715b5e172b64a7518cb0e02cdaf4b11e244a6"

09 Dec, 2025 1 commit
- [Perf] Optimize `group_topk` kernel, 1.9% Throughput improvement, 2.1% TPOT improvemnt (#30159) · 0ee6416f
  Wentao Ye authored Dec 08, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  0ee6416f
08 Nov, 2025 1 commit

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124) · 08525276

Michael Goin authored Nov 08, 2025

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>

08525276

23 Sep, 2025 1 commit

Use macro guard CUDA functions for back compatibility in grouped_topk_kernel.cu (#25346) · 527821d1

Ming Yang authored Sep 23, 2025


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>

527821d1

18 Sep, 2025 1 commit
- [Kernel] Better inf handling for grouped topk cu (#24886) · 81b16a2b
  Lumina authored Sep 18, 2025
```
Signed-off-by: lumina37 <starry.qvq@gmail.com>
```
  81b16a2b
04 Sep, 2025 1 commit
- [Kernel][Bugfix] Fix grouped topk cu (#24146) · e919d6f5
  Qiming Zhang authored Sep 03, 2025
```
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
```
  e919d6f5
25 Aug, 2025 1 commit

[Kernel] Add fused grouped_topk kernel for MoE (#23274) · 8a3cd90a

Xin Yang authored Aug 25, 2025


Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

8a3cd90a