llama.cpp
CUDA: fuse SSM_CONV + ADD(bias) + SILU
#22478
Merged

CUDA: fuse SSM_CONV + ADD(bias) + SILU #22478

anavp-nvidia
anavp-nvidia anavp-nvidia requested a review from ggerganov ggerganov 45 days ago
anavp-nvidia anavp-nvidia requested a review 45 days ago
am17an
am17an commented on 2026-04-28
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
gaugarg-nv
gaugarg-nv commented on 2026-04-28
anavp-nvidia CUDA: ssm_conv + bias + silu fusion
f8742f86
anavp-nvidia Apply suggestions from code review
aa960f73
anavp-nvidia adding back accidentally deleted line
3a7085f7
anavp-nvidia anavp-nvidia force pushed from 6410eb78 to 3a7085f7 44 days ago
ORippler
ORippler commented on 2026-04-29
anavp-nvidia simplify ssm_conv fusion templating and test struct
373ca030
am17an
am17an approved these changes on 2026-04-29
ggerganov
ggerganov approved these changes on 2026-04-29
am17an am17an merged 098705a2 into master 43 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone