AutoGPTQ/auto_gptq/nn_modules/qlinear
2023-08-17 15:19:01 +09:00
..
__init__.py regist buffer of general quant linear 2023-08-03 05:15:09 +00:00
qlinear_cuda.py fix fused attn 2023-07-31 13:46:32 +00:00
qlinear_cuda_old.py fix fused attn 2023-07-31 13:46:32 +00:00
qlinear_exllama.py patch for transformers compatiblity 2023-08-09 14:23:59 +00:00
qlinear_qigen.py qigen formatting qlinear 2023-08-17 15:19:01 +09:00
qlinear_triton.py fix fused attn 2023-07-31 13:46:32 +00:00