onnxruntime
[CUDA] Coalesce QMoE MXFP4/NVFP4 weight dequantization
#31349
Merged

[CUDA] Coalesce QMoE MXFP4/NVFP4 weight dequantization #31349

tianleiwu
tianleiwu [CUDA] Coalesce QMoE MXFP4/NVFP4 weight dequantization
58347e02
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 2026-08-01
tianleiwu fix(cuda): use __uint_as_float in DecodeFp4E2M1
db44c8ed
tianleiwu tianleiwu requested a review from baijumeswani baijumeswani 8 days ago
tianleiwu tianleiwu requested a review from hariharans29 hariharans29 8 days ago
tianleiwu tianleiwu requested a review from kunal-vaishnavi kunal-vaishnavi 8 days ago
tianleiwu tianleiwu requested a review from titaiwangms titaiwangms 8 days ago
kunal-vaishnavi
kunal-vaishnavi approved these changes on 2026-08-03
kunal-vaishnavi kunal-vaishnavi merged e5d4a891 into main 7 days ago
kunal-vaishnavi kunal-vaishnavi deleted the tlwu/20260731/qmoe_fp4_dequant_coalesced branch 7 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone