AlpinDale 968bde81bf fix: tensor parallel with GPTQ and AWQ quants (#307) 10 ماه پیش
..
layers 968bde81bf fix: tensor parallel with GPTQ and AWQ quants (#307) 10 ماه پیش
megatron c2d77b1822 chore: logging refactor (#302) 10 ماه پیش
models c41462cfcd feat: exllamav2 quantization (#305) 10 ماه پیش
__init__.py 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 سال پیش
hf_downloader.py c41462cfcd feat: exllamav2 quantization (#305) 10 ماه پیش
loader.py c2d77b1822 chore: logging refactor (#302) 10 ماه پیش
metadata.py 9810daa699 feat: INT8 KV Cache (#298) 10 ماه پیش
outlines_decoding.py 657aec0cbd refactor: OpenAI endpoint (#261) 10 ماه پیش
outlines_logits_processors.py 657aec0cbd refactor: OpenAI endpoint (#261) 10 ماه پیش
sampling_metadata.py 9fa99215f8 feat: add cubic sampling (#280) 10 ماه پیش
utils.py 2755a48d51 merge dev branch into main (#153) 1 سال پیش