Skip to content

Fix SpinQuant -> Quip link #2011

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
merged 1 commit into from
Nov 10, 2025
Merged

Fix SpinQuant -> Quip link #2011

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions examples/transform/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ recipe = [
]
```

Note that `QuIPModifier` can be customized. For a full list of the available arguments, see the [docstring](/src/llmcompressor/modifiers/transform/spinquant/base.py) or documentation.
Note that `QuIPModifier` can be customized. For a full list of the available arguments, see the [docstring](/src/llmcompressor/modifiers/transform/quip/base.py) or documentation.

* `rotations` determines which of the input rotation (v) or output rotations (u) should be used.
* `transform_block_size` determines the size of the hadamard. Smaller hadamards require less cost at runtime.
Expand Down Expand Up @@ -79,4 +79,4 @@ python3 benchmarks/benchmark_latency.py --model path/to/Llama-3.2-1B-Instruct-qu
#### Quantized Model Latency (sec) ####
| Base W4A16 | Hadacore | GEMM |
| - | - | - |
| 0.4402 | 0.4489 | 1.2917 |
| 0.4402 | 0.4489 | 1.2917 |
Loading