7 commits

Author	SHA1	Message	Date
Concedo	8bf2e50a11	converted the cl file to be a string literal instead	2023-04-16 15:57:30 +08:00
0cc4m	57d046eeb6	Enable dequantization on GPU for ClBlast	2023-04-15 18:04:24 +02:00
0cc4m	67d220210f	Revert buffer changes, no improvements in benchmarks	2023-04-12 23:10:35 +02:00
0cc4m	c7e5c4f7b2	Improve ClBlast implementation, avoid recreating buffers, remove redundant transfers	2023-04-12 23:10:33 +02:00
Concedo	4faae0afa9	Merged upstream, fixed OSX compile errors, integrated noavx2 build into main	2023-04-12 18:08:55 +08:00
Concedo	ca69e05d1f	update readme and fixed typos	2023-04-11 23:53:21 +08:00
Concedo	23c675b2e6	integrated optional (experimentl) CLBlast support	2023-04-11 23:33:44 +08:00