AlpinDale 3f92035bf1 fix: add `ignored_seq_groups` in `_schedule_chunked_prefill` vor 7 Monaten
..
attention 75f97bc25d bump flash-attn to remove unnecessary copies in the backend vor 7 Monaten
common 76d6f49bbb fix: modelscope downloads vor 7 Monaten
distributed b2fd915c35 improve p2p access check vor 7 Monaten
endpoints 1d7f5c45b0 feat: add stream_options for chat completions vor 7 Monaten
engine d7ebffe2f0 chore: re-add the graceful engine shutdown vor 7 Monaten
executor 17eb1b7eb9 chore: remove ray health check vor 7 Monaten
kv_quant e42a78381a feat: switch from pylint to ruff (#322) vor 1 Jahr
lora c975bba905 fix: sharded state loader with lora vor 7 Monaten
modeling c975bba905 fix: sharded state loader with lora vor 7 Monaten
multimodal f2e94e2184 chore: minor llava cleanups in preparation for llava-next vor 7 Monaten
processing 3f92035bf1 fix: add `ignored_seq_groups` in `_schedule_chunked_prefill` vor 7 Monaten
quantization 40bc98b363 chore: use cutlass kernels for fp8 if supported vor 7 Monaten
spec_decode ec5b99d075 fix: use named args vor 7 Monaten
task_handler c975bba905 fix: sharded state loader with lora vor 7 Monaten
transformers_utils 76d6f49bbb fix: modelscope downloads vor 7 Monaten
__init__.py be8154a8a0 feat: proper embeddings API with e5-mistral-7b support vor 7 Monaten
py.typed 1c988a48b2 fix logging and add py.typed vor 1 Jahr