llama.cpp

mirror of https://github.com/ggerganov/llama.cpp.git

3,096 Commits 543 Branches 5,622 Tags 1.5 GiB

Author	SHA1	Message	Date
slaren	63e06d0c28	reuse main thread	2024-06-07 09:55:15 +02:00
slaren	2dd049ed45	ggml-ci	2024-06-07 02:58:42 +02:00
slaren	0425305d32	fix apple build	2024-06-07 01:57:02 +02:00
slaren	2bfdb7fe4e	support multithreaded dequantization with std::async when openmp is not available	2024-06-06 03:12:50 +02:00

Renamed from ggml-blas.c (Browse further)