b11543: vulkan: use 4 rows for NVIDIA MUL_MAT_ID MMVQ (#29274)
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
Keep the existing RDNA3/4 policy unchanged and update only rm_id to use 4 rows for NVIDIA except pre-Turing.
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.