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

[Docs] fixed minor typo (#29555)

Browse Source
This commit is contained in:
j-gc
2024-03-11 16:35:16 +05:30
committed by GitHub
parent 4f27ee936a
commit d80c9a3497
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.md
View File

@@ -49,7 +49,7 @@ Starting with version `aqlm 1.0.2`, AQLM supports Parameter-Efficient Fine-Tunin
### AQLM configurations ### AQLM configurations
AQLM quantization setpus vary mainly on the number of codebooks used as well as codebook sizes in bits. The most popular setups, as well as inference kernels they support are: AQLM quantization setups vary mainly on the number of codebooks used as well as codebook sizes in bits. The most popular setups, as well as inference kernels they support are:
| Kernel | Number of codebooks | Codebook size, bits | Notation | Accuracy | Speedup | Fast GPU inference | Fast CPU inference | | Kernel | Number of codebooks | Codebook size, bits | Notation | Accuracy | Speedup | Fast GPU inference | Fast CPU inference |
|---|---------------------|---------------------|----------|-------------|-------------|--------------------|--------------------| |---|---------------------|---------------------|----------|-------------|-------------|--------------------|--------------------|