SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Doc] Fix int8 docs (#21487)

Browse Source 
fix int8 docs
This commit is contained in:
Younes Belkada
2023-02-07 15:09:27 +01:00
committed by GitHub
parent 1e4cf8bb44
commit fa0ae17958
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/perf_infer_gpu_one.mdx
View File

@@ -40,7 +40,7 @@ Below are some notes to help you use this module, or follow the demos on [Google
### Requirements ### Requirements
- Make sure you run on NVIDIA GPUs that support 8-bit tensor cores (Turing, Ampere or newer architectures - e.g. T4, RTX20s RTX30s, A40-A100). - If you have `bitsandbytes<0.37.0`, make sure you run on NVIDIA GPUs that support 8-bit tensor cores (Turing, Ampere or newer architectures - e.g. T4, RTX20s RTX30s, A40-A100). For `bitsandbytes>=0.37.0`, all GPUs should be supported.
- Install the correct version of `bitsandbytes` by running: - Install the correct version of `bitsandbytes` by running:
`pip install bitsandbytes>=0.31.5` `pip install bitsandbytes>=0.31.5`
- Install `accelerate` - Install `accelerate`