2 Commits

Author	SHA1	Message	Date
John Smith	9351f49542	merge pull request in new branch	2023-04-07 10:40:24 +08:00
Andrey Glushenkov	f20570343f	GPTQv2 support ... GPTQv2 support. 1. Adds dependency on `triton` 2. Refactors autograd_4bit to include both GPTQv1 and GPTQv2 3. Introduces new environment variable GPTQ_VERSION to select autograd_4bit version 4. Fixes triton kernels 5. Matrix multiplications are in fp16	2023-04-06 02:29:36 +03:00