Skip to content

Update QAT docs, highlight axolotl integration #2266

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
andrewor14 merged 4 commits into from
Jun 10, 2025
Merged

Update QAT docs, highlight axolotl integration #2266

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b435f30
updating docs
salmanmohammadi May 28, 2025
c9b0fa9
updating docs
salmanmohammadi May 28, 2025
6ec512e
updating docs
salmanmohammadi May 28, 2025
14cc86d
updating qat readme
salmanmohammadi May 29, 2025
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
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,6 +213,7 @@ We're also fortunate to be integrated into some of the leading open-source libra
4. [TorchTune](https://pytorch.org/torchtune/main/tutorials/qlora_finetune.html?highlight=qlora) for our QLoRA and QAT recipes
5. VLLM for LLM serving: [usage](https://docs.vllm.ai/en/latest/features/quantization/torchao.html)
6. SGLang for LLM serving: [usage](https://docs.sglang.ai/backend/server_arguments.html#server-arguments) and the major [PR](https://github.com/sgl-project/sglang/pull/1341).
7. Axolotl for [QAT](https://docs.axolotl.ai/docs/qat.html) and [PTQ](https://docs.axolotl.ai/docs/quantize.html)

## Videos
* [Keynote talk at GPU MODE IRL](https://youtu.be/FH5wiwOyPX4?si=VZK22hHz25GRzBG1&t=1009)
Expand Down
15 changes: 12 additions & 3 deletions torchao/quantization/qat/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,11 +115,20 @@ To fake quantize embedding in addition to linear, you can additionally call
the following with a filter function during the prepare step:

Copy link
Contributor

@andrewor14 andrewor14 May 29, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There's a section below that says "torchtune integration". Can you add a similar section for "Axolotl Integration" and add a small code snippet there?

```
from torchao.quantization.quant_api import _is_linear
# first apply linear transformation to the model as above
activation_config = FakeQuantizeConfig(torch.int8, "per_token", is_symmetric=False)
weight_config = FakeQuantizeConfig(torch.int4, group_size=32)
quantize_(
model,
IntXQuantizationAwareTrainingConfig(activation_config, weight_config),
)

# then apply weight-only transformation to embedding layers
# activation fake quantization is not supported for embedding layers
quantize_(
m,
IntXQuantizationAwareTrainingConfig(weight_config=weight_config),
filter_fn=lambda m, _: isinstance(m, torch.nn.Embedding) or _is_linear(m),
IntXQuantizationAwareTrainingConfig(weight_config=weight_config),
filter_fn=lambda m, _: isinstance(m, torch.nn.Embedding)
)
```

Expand Down