amritahs-ibm b7b38f7d68 ggml : optimize llamafile cpu matrix multiplication for ppc64le (llama/10156) ... This change upstreams llamafile's cpu matrix multiplication kernels for ppc64le using MMA builtins for FP32 datatype. This change results in a consistent 90% improvement in input processing time, and 20% to 80% improvement in output processing time, across various batch sizes. The patch is tested with Meta-Lllama-3-8B, Mistral-7B, Llama-2-7B-chat-hf models on a IBM POWER10 machine. Signed-off-by: Amrita H S <amritahs@linux.vnet.ibm.com>		2024-11-15 15:21:04 +02:00
..
cmake	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00
include	metal : optimize FA kernels (llama/10171)	2024-11-15 15:21:04 +02:00
src	ggml : optimize llamafile cpu matrix multiplication for ppc64le (llama/10156)	2024-11-15 15:21:04 +02:00
.gitignore	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00
CMakeLists.txt	metal : opt-in compile flag for BF16 (llama/10218)	2024-11-15 15:21:04 +02:00
ggml_vk_generate_shaders.py	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00