3 Commits

Author	SHA1	Message	Date
Kawrakow	1a4cfbcc53	Merge mainline - Aug 12 2024 (#17) ... * Merge mainline * Fix after merge * Remove CI check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2024-08-12 15:14:32 +02:00
Kawrakow	8654a425ae	Factor out iqk CUDA dot products ... I cannot possibly wait for a 5 minutes nvcc compilation each time I touch vecdotq.cuh. Also, cmake was adding --options-file X.rsp to the nvcc compile commands, which confuses clangd, so I have turned that off.	2024-08-01 09:38:06 +02:00
Kawrakow	0ceeb11721	Merge mainline llama.cpp (#3) ... * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2024-07-27 07:55:01 +02:00