5 Commits

Author	SHA1	Message	Date
John Smith	633c28fd25	add quant attn v1 support	2023-04-25 12:30:03 +08:00
John Smith	b5af5c00e1	optimize lora compute	2023-04-25 09:18:51 +08:00
John Smith	9fe5ab3642	fix bug	2023-04-22 17:24:07 +08:00
John Smith	eb442494d1	optimize mem usage	2023-04-22 16:35:18 +08:00
John Smith	de3c91834e	optimized attention and mlp for performance, add lora monkey patch for models here and GPTQ_For_Llama models using optimization	2023-04-22 15:36:56 +08:00