Kawrakow 154e0d75fc 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
..
nix	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
cloud-v-pipeline	build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
full-cuda.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
full-rocm.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
full.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cli-cuda.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cli-intel.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cli-rocm.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cli-vulkan.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cli.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cpp-cuda.srpm.spec	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-cpp.srpm.spec	build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
llama-server-cuda.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-server-intel.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-server-rocm.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-server-vulkan.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
llama-server.Dockerfile	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
tools.sh	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00