simcop2387/AutoGPTQ
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity
AutoGPTQ/auto_gptq/nn_modules/qlinear
History
PanQiWei 69609c4bc7 support faster vecquant4matmul cuda kernel
2023-05-26 08:55:05 +08:00
..
__init__.py refactor file structure of qlinears 2023-05-26 07:18:16 +08:00
qlinear_cuda.py support faster vecquant4matmul cuda kernel 2023-05-26 08:55:05 +08:00
qlinear_cuda_old.py refactor file structure of qlinears 2023-05-26 07:18:16 +08:00
qlinear_triton.py refactor file structure of qlinears 2023-05-26 07:18:16 +08:00