AlpinDale 5b0c11d190 support pipeline parallel pynccl groups 6 месяцев назад
..
__init__.py 2bd6c92f73 fix: lora inclusion in wheels 1 год назад
fully_sharded_layers.py e87c32bed3 feat: full tensor parallel for LoRA layers (#545) 6 месяцев назад
layers.py 9e73559eba make use of batched rotary embedding kernels to support long context lora 6 месяцев назад
lora.py e87c32bed3 feat: full tensor parallel for LoRA layers (#545) 6 месяцев назад
models.py 9e73559eba make use of batched rotary embedding kernels to support long context lora 6 месяцев назад
punica.py e87c32bed3 feat: full tensor parallel for LoRA layers (#545) 6 месяцев назад
request.py 5b0c11d190 support pipeline parallel pynccl groups 6 месяцев назад
utils.py 9e73559eba make use of batched rotary embedding kernels to support long context lora 6 месяцев назад
worker_manager.py 9e73559eba make use of batched rotary embedding kernels to support long context lora 6 месяцев назад