llama.cpp
cuda: enable topk-moe fusion for 288 experts
#25267
Merged

cuda: enable topk-moe fusion for 288 experts #25267

pwilkin
pwilkin pwilkin requested a review from ggerganov ggerganov 13 days ago
pwilkin pwilkin requested a review 13 days ago
github-actions github-actions added testing
github-actions github-actions added ggml
github-actions github-actions added CUDA
pwilkin cuda: enable topk-moe fusion for 288 experts
5de3e408
pwilkin pwilkin force pushed from b3a3ee27 to 5de3e408 13 days ago
ORippler
ORippler approved these changes on 2026-07-03
pwilkin Update tests/test-backend-ops.cpp
c46bc26f
pwilkin Add comment for case 288 in topk-moe.cu
c685c033
pwilkin
ruixiang63
ruixiang63 approved these changes on 2026-07-03
pwilkin pwilkin merged 75a48a90 into master 13 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone