onnxruntime
Add BF16 routing support to CUDA MoE
#32659
Merged

Add BF16 routing support to CUDA MoE #32659

kunal-vaishnavi merged 2 commits into main from kvaishnavi/moe-bf16-cuda
kunal-vaishnavi
kunal-vaishnavi Add BF16 routing support to CUDA MoE
ff803f2c
kunal-vaishnavi kunal-vaishnavi requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 6 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
kunal-vaishnavi Test BF16 sparse mixer routing
80f4f667
apsonawane
apsonawane approved these changes on 2026-09-16
kunal-vaishnavi kunal-vaishnavi enabled auto-merge (squash) 6 days ago
kunal-vaishnavi kunal-vaishnavi merged e266b17e into main 6 days ago
kunal-vaishnavi kunal-vaishnavi deleted the kvaishnavi/moe-bf16-cuda branch 6 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone