| .. |
|
attention
|
46159b107a
formatting: pt1
|
6 months ago |
|
common
|
737f1c3351
part 1
|
6 months ago |
|
distributed
|
d1a3c7bc2c
chore: simplify try-finally logic in pynccl
|
6 months ago |
|
endpoints
|
46159b107a
formatting: pt1
|
6 months ago |
|
engine
|
737f1c3351
part 1
|
6 months ago |
|
executor
|
41338053e7
feat: add shutdown method to engine
|
6 months ago |
|
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
9 months ago |
|
lora
|
8be299e78b
fix: lora load check
|
7 months ago |
|
modeling
|
737f1c3351
part 1
|
6 months ago |
|
processing
|
737f1c3351
part 1
|
6 months ago |
|
quantization
|
46159b107a
formatting: pt1
|
6 months ago |
|
spec_decode
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 months ago |
|
task_handler
|
2e0b115ce1
move func tracing to utils
|
6 months ago |
|
transformers_utils
|
ed759f065d
chore: tokenizer_revision -> revision
|
6 months ago |
|
__init__.py
|
199e776722
chore: move ray utils to executor dir
|
6 months ago |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
AlpinDale
737f1c3351
part 1