huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-27 04:52:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc: clarify that --quantize is not needed for pre-quantized models (#2536)

Browse Source
This commit is contained in:
Daniël de Kok 2024-09-19 22:17:15 +02:00 committed by yuanwu
parent c1a99e2f15
commit b6ef2bfc1b
3 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/reference/launcher.md
View File

@ -55,7 +55,9 @@ Options:
## QUANTIZE ## QUANTIZE
```shell ```shell
--quantize <QUANTIZE> --quantize <QUANTIZE>
Whether you want the model to be quantized Quantization method to use for the model. It is not necessary to specify this option for pre-quantized models, since the quantization method is read from the model configuration.
Marlin kernels will be used automatically for GPTQ/AWQ models.
[env: QUANTIZE=] [env: QUANTIZE=]

1
flake.nix
View File

@ -157,6 +157,7 @@
pyright pyright
pytest pytest
pytest-asyncio pytest-asyncio
redocly
ruff ruff
syrupy syrupy
]); ]);

6
launcher/src/main.rs
View File

@ -369,7 +369,11 @@ struct Args {
#[clap(long, env)] #[clap(long, env)]
num_shard: Option<usize>, num_shard: Option<usize>,
/// Whether you want the model to be quantized. /// Quantization method to use for the model. It is not necessary to specify this option
/// for pre-quantized models, since the quantization method is read from the model
/// configuration.
///
/// Marlin kernels will be used automatically for GPTQ/AWQ models.
#[clap(long, env, value_enum)] #[clap(long, env, value_enum)]
quantize: Option<Quantization>, quantize: Option<Quantization>,