vllm/quantization at 3a886bd58cecf3ce78c1eafed1f7d3d16800bccc - vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 00:25:49 +08:00

History

Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>

2025-05-25 06:05:38 -07:00

auto_awq.md

[doc] improve readability (#18675 )

2025-05-25 01:40:31 -07:00

bitblas.md

[doc] improve readability (#18675 )

2025-05-25 01:40:31 -07:00

bnb.md

[Misc] small improve (#18680 )

2025-05-25 06:05:38 -07:00

fp8.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

gguf.md

[doc] improve readability (#18675 )

2025-05-25 01:40:31 -07:00

gptqmodel.md

[doc] improve readability (#18675 )

2025-05-25 01:40:31 -07:00

int4.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

int8.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

modelopt.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

quantized_kvcache.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

quark.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

README.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

supported_hardware.md

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

torchao.md

[doc] improve readability (#18675 )

2025-05-25 01:40:31 -07:00

README.md

title
Quantization

{ #quantization-index }

Quantization trades off model precision for smaller memory footprint, allowing large models to be run on a wider range of devices.

Contents: