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

[docs] add XPU besides CUDA, MPS etc. (#34777)

Browse Source 
add XPU
This commit is contained in:
Fanli Lin
2024-11-19 01:58:50 +08:00
committed by GitHub
parent 8568bf1bcf
commit 9568a9dfc5
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/quantization/quanto.md
View File

@@ -28,7 +28,7 @@ Try Quanto + transformers with this [notebook](https://colab.research.google.com
- weights quantization (`float8`,`int8`,`int4`,`int2`) - weights quantization (`float8`,`int8`,`int4`,`int2`)
- activation quantization (`float8`,`int8`) - activation quantization (`float8`,`int8`)
- modality agnostic (e.g CV,LLM) - modality agnostic (e.g CV,LLM)
- device agnostic (e.g CUDA,MPS,CPU) - device agnostic (e.g CUDA,XPU,MPS,CPU)
- compatibility with `torch.compile` - compatibility with `torch.compile`
- easy to add custom kernel for specific device - easy to add custom kernel for specific device
- supports quantization aware training - supports quantization aware training