Skip to content

review: update docs #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jiqing-feng merged 2 commits into from
Dec 24, 2024
Merged

review: update docs #12

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d35689
review: update docs
Qubitium Dec 24, 2024
b3353ac
fix typo
Qubitium Dec 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions docs/source/en/quantization/gptq.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,14 @@ model = AutoModelForCausalLM.from_pretrained("{your_username}/opt-125m-gptq", de

[Marlin](https://github.com/IST-DASLab/marlin) is a CUDA gptq kernel, 4-bit only, that is highly optimized for the Nvidia A100 GPU (Ampere) architecture where the the loading, dequantization, and execution of post-dequantized weights are highly parallelized offering a substantial inference improvement versus the original CUDA gptq kernel. Marlin is only available for quantized inference and does support model quantization.

Marlin inference can be activated via the `backend` property in `GPTQConfig` for GPTQModel:

```py

from transformers import AutoModelForCausalLM, GPTQConfig

model = AutoModelForCausalLM.from_pretrained("{your_username}/opt-125m-gptq", device_map="auto", quantization_config=GPTQConfig(bits=4, backend="marlin"))
```

## ExLlama

Expand Down