fxmarty 650fea1834 GPTQ support on ROCm (#1489) ... Tested with ``` CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq EXLLAMA_VERSION=1 CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq CUDA_VISIBLE_DEVICES="0,1" text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq ``` all with good and identical results on MI210. --------- Co-authored-by: Felix Marty <felix@hf.co> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>		2024-01-26 16:27:44 +01:00
..
custom_autotune.py	fix: fix quant linear autotune	2023-12-14 16:45:47 +01:00
exllama.py	fix: fix gpt-q with groupsize = -1 (#1358)	2023-12-18 16:07:05 +01:00
exllamav2.py	GPTQ support on ROCm (#1489)	2024-01-26 16:27:44 +01:00
quant_linear.py	Fixing non 4bits quantization. (#785)	2023-08-07 13:02:00 +02:00
quantize.py	feat: format code (#1070)	2023-09-27 12:22:09 +02:00