Add exllama GPTQ CUDA kernel support#553
Closed
fxmarty wants to merge 27 commits intohuggingface:main from fxmarty:gptq-cuda-kernels
+3,317-66
Commits
Commits on Jul 5, 2023
- committed
- committed
- committed
- committed
Merge branch 'gptq-cuda-kernels' of https://github.com/fxmarty/text-generation-inference into gptq-cuda-kernels
committed- committed
Commits on Jul 12, 2023
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Commits on Jul 13, 2023
- committed
- committed
- committed
- committed
Commits on Jul 19, 2023
Commits on Jul 20, 2023
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Commits on Jul 21, 2023
- committed