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