onnxruntime
[CUDA][QMoE] Wire LaunchFusedRouteMaps into CutlassMoeFCRunner for S<=8 and E<=512
#33596
Merged

[CUDA][QMoE] Wire LaunchFusedRouteMaps into CutlassMoeFCRunner for S<=8 and E<=512 #33596

tianleiwu
tianleiwu Wire LaunchFusedRouteMaps into CutlassMoeFCRunner for multi-token/512…
966d111b
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 10 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-10-25
tianleiwu tianleiwu added model:qwen-3.8
tianleiwu fix(cuda): declare CanUseFusedRouteMaps, fix LaunchFusedRouteMaps cal…
32902810
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 9 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-10-26
kunal-vaishnavi
kunal-vaishnavi commented on 2026-10-27
apsonawane
apsonawane approved these changes on 2026-10-27
tianleiwu tianleiwu merged a3c3cf98 into main 8 days ago
tianleiwu tianleiwu deleted the tlwu/20261025/qmoe-fused-route-maps branch 8 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone