dev-python/autoawq
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
Runtime Dependencies
autoawq-0.2.9
dev-python/torch[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/triton[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/transformers[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/tokenizers[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
>=dev-python/typing-extensions-4.8.0[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/accelerate[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/datasets[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/zstandard[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
dev-python/huggingface-hub[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
]
eval?
( dev-python/lm-eval[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
eval?
( dev-python/tabulate[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
eval?
( dev-python/protobuf[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
eval?
( dev-python/evaluate[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
eval?
( dev-python/scipy[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
dev?
( dev-python/black[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
dev?
( dev-python/mkdocstrings-python[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
dev?
( dev-python/mkdocs-material[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
dev?
( dev-python/griffe-typingdoc[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
cpu?
( dev-python/intel-extension-for-pytorch[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
kernels?
( dev-python/autoawq-kernels[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
kernels?
( dev-python/flash-attn[python_targets_python3_11
(-)
?
,python_targets_python3_12
(-)
?
,python_targets_python3_13
(-)
?
,python_targets_python3_14
(-)
?
] )
python_targets_python3_11?
( dev-lang/python:3.11 )
python_targets_python3_12?
( dev-lang/python:3.12 )
python_targets_python3_13?
( dev-lang/python:3.13 )
python_targets_python3_14?
( dev-lang/python:3.14 )


View
Download
Browse