b11456: ggml-cuda: use per-thread stream for buffer-init padding memset (#28782)
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
-
ggml-cuda: use per-thread stream for buffer-init padding memset
-
ci : re-enable test-backend-ops -j for ROCm
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.