onnxruntime
[CUDA] Skip FP4 QMoE fc1 activation expansion
#31479
Open

[CUDA] Skip FP4 QMoE fc1 activation expansion #31479

tianleiwu wants to merge 1 commit into main from tlwu/20260802/nvfp4_moe_skip_expand
tianleiwu
tianleiwu tianleiwu force pushed from c62b6aed to f713813a 1 day ago
tianleiwu tianleiwu force pushed from f713813a to 77dc84d7 1 day ago
Base automatically changed from tlwu/20260730/nvfp4_moe_gemv to main 21 hours ago
tianleiwu tianleiwu force pushed from 77dc84d7 to b964e92b 21 hours ago
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 5 hours ago
tianleiwu [CUDA] Skip FP4 QMoE fc1 activation expansion
f46110e2
tianleiwu tianleiwu force pushed from b964e92b to f46110e2 5 hours ago
tianleiwu tianleiwu requested a review from hariharans29 hariharans29 5 hours ago
tianleiwu tianleiwu requested a review from kunal-vaishnavi kunal-vaishnavi 5 hours ago
tianleiwu tianleiwu requested a review from titaiwangms titaiwangms 5 hours ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-08-06
titaiwangms

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone