Ilyas Moutawwakil 4fc708f98c Exllama kernels support for AWQ models (#28634) ... * added exllama kernels support for awq models * doc * style * Update src/transformers/modeling_utils.py Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> * refactor * moved exllama post init to after device dispatching * bump autoawq version * added exllama test * style * configurable exllama kernels * copy exllama_config from gptq * moved exllama version check to post init * moved to quantization dockerfile --------- Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>		2024-03-05 03:22:48 +01:00
..
transformers-all-latest-gpu	Use torch 2.2 for daily CI (model tests) (#29208)	2024-02-23 21:37:08 +08:00
transformers-doc-builder	Use python 3.10 for docbuild (#28399)	2024-01-11 14:39:49 +01:00
transformers-gpu	TF: TF 2.10 unpin + related onnx test skips (#18995)	2022-09-12 19:30:27 +01:00
transformers-past-gpu	Byebye pytorch 1.9 (#24080)	2023-06-16 16:38:23 +02:00
transformers-pytorch-amd-gpu	Add deepspeed test to amd scheduled CI (#27633)	2023-12-11 16:33:36 +01:00
transformers-pytorch-deepspeed-amd-gpu	Add deepspeed test to amd scheduled CI (#27633)	2023-12-11 16:33:36 +01:00
transformers-pytorch-deepspeed-latest-gpu	Use torch 2.2 for deepspeed CI (#29246)	2024-02-27 17:51:37 +08:00
transformers-pytorch-deepspeed-nightly-gpu	Update CUDA versions for DeepSpeed (#27853)	2023-12-05 16:15:21 -05:00
transformers-pytorch-gpu	[SDPA] Make sure attn mask creation is always done on CPU (#28400)	2024-01-09 11:05:19 +01:00
transformers-pytorch-tpu	Rename master to main for notebooks links and leftovers (#16397)	2022-03-25 09:12:23 -04:00
transformers-quantization-latest-gpu	Exllama kernels support for AWQ models (#28634)	2024-03-05 03:22:48 +01:00
transformers-tensorflow-gpu	Update TF pin in docker image (#25343)	2023-08-07 12:32:34 +02:00