b11590
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
vulkan : split matmul dispatch when it would exceed maxComputeWorkGro…
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
vulkan : split matmul dispatch when it would exceed maxComputeWorkGro…
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.