AlpinDale 71a26f0998 chore: use pytorch sdpa backend to do naive attention for rocm 7 hónapja
..
attention 71a26f0998 chore: use pytorch sdpa backend to do naive attention for rocm 7 hónapja
common 76d6f49bbb fix: modelscope downloads 7 hónapja
distributed b2fd915c35 improve p2p access check 7 hónapja
endpoints 1d7f5c45b0 feat: add stream_options for chat completions 7 hónapja
engine d7ebffe2f0 chore: re-add the graceful engine shutdown 7 hónapja
executor 17eb1b7eb9 chore: remove ray health check 7 hónapja
kv_quant e42a78381a feat: switch from pylint to ruff (#322) 1 éve
lora c975bba905 fix: sharded state loader with lora 7 hónapja
modeling b2cb5a92e9 fix: missing cache_config for dbrx 7 hónapja
multimodal f2e94e2184 chore: minor llava cleanups in preparation for llava-next 7 hónapja
processing 3f92035bf1 fix: add `ignored_seq_groups` in `_schedule_chunked_prefill` 7 hónapja
quantization e9c0a248dc fix: support check for fp8 cutlass 7 hónapja
spec_decode ec5b99d075 fix: use named args 7 hónapja
task_handler c975bba905 fix: sharded state loader with lora 7 hónapja
transformers_utils 76d6f49bbb fix: modelscope downloads 7 hónapja
__init__.py be8154a8a0 feat: proper embeddings API with e5-mistral-7b support 7 hónapja
py.typed 1c988a48b2 fix logging and add py.typed 1 éve