4 Commits

Author	SHA1	Message	Date
laurent	3fa3623135	Faster matmul when we can fall back to gemv.	2023-08-04 22:44:30 +01:00
Laurent Mazare	f7b2a0391d	Transpose the weight matrixes for llama2.c. (#321)	2023-08-04 13:32:20 +01:00
Laurent Mazare	a79286885c	Support safetensors weights in llama2.c inference. (#317)	2023-08-03 11:10:58 +01:00
Laurent Mazare	75e0448114	Move the weight bits in a separate module. (#295)	2023-08-01 10:37:06 +01:00