llama.cpp
Enable CUDA graph for MTP draft
#28549
Merged

Enable CUDA graph for MTP draft #28549

gaugarg-nv merged 3 commits into ggml-org:master from gaugarg-nv:mtp_graph
gaugarg-nv
gaugarg-nv gaugarg-nv requested a review from ggerganov ggerganov 62 days ago
ruixiang63
ruixiang63 approved these changes on 2026-09-07
gaugarg-nv gaugarg-nv force pushed 62 days ago
am17an
ruixiang63
am17an
aendk
ruixiang63
am17an
ruixiang63
am17an
gaugarg-nv
am17an
ruixiang63
am17an
aendk
am17an
gaugarg-nv
am17an
am17an approved these changes on 2026-09-15
ggerganov
ggerganov
gaugarg-nv Improve CUDA graph usage for MTP
d9f734b1
gaugarg-nv Rename field
81144979
gaugarg-nv
ggerganov
gaugarg-nv Address review feedback
a44e6824
gaugarg-nv gaugarg-nv force pushed to a44e6824 53 days ago
gaugarg-nv
am17an
gaugarg-nv
ggerganov
ggerganov approved these changes on 2026-09-16
gaugarg-nv gaugarg-nv merged 2f3fd025 into master 53 days ago
gaugarg-nv gaugarg-nv deleted the mtp_graph branch 53 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone