Skip to content

Update quantization.md #483

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 2 commits into from
Apr 25, 2024
Merged

Update quantization.md #483

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
95e227e
Update quantization.md
jerryzh168 Apr 25, 2024
9f902f7
Update quantization.md
jerryzh168 Apr 25, 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
6 changes: 2 additions & 4 deletions docs/quantization.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,15 +239,13 @@ python3 generate.py [ --pte-path ${MODEL_OUT}/${MODEL_NAME}_a8w4dq.pte | ...dso.
## 4-bit Integer Linear Quantization with GPTQ (gptq)
Compression offers smaller memory footprints (to fit on memory-constrained accelerators and mobile/edge devices) and reduced memory bandwidth (for better performance), but often at the price of quality degradation. GPTQ 4-bit integer quantization may be used to reduce the quality impact. To achieve good accuracy, we recommend the use of groupwise quantization where (small to mid-sized) groups of int4 weights share a scale.

**TODO (Jerry): GPTQ quantization documentation [#336](https://github.com/pytorch/torchchat/issues/336) **

We can use GPTQ with eager execution, optionally in conjunction with torch.compile:
```
python3 generate.py [--compile] --checkpoint-path ${MODEL_PATH} --prompt "Hello, my name is" --quantize '{"linear:int4" : {"groupsize": 32}}' --device [ cpu | cuda | mps ]
python3 generate.py [--compile] --checkpoint-path ${MODEL_PATH} --prompt "Hello, my name is" --quantize '{"linear:int4-gptq" : {"groupsize": 32}}' --device [ cpu | cuda | mps ]
```

```
python3 export.py --checkpoint-path ${MODEL_PATH} -d fp32 --quantize '{"linear:gptq": {"groupsize" : 32} }' [ --output-pte-path ${MODEL_OUT}/${MODEL_NAME}_gptq.pte | ...dso... ]
python3 export.py --checkpoint-path ${MODEL_PATH} -d fp32 --quantize '{"linear:int4-gptq": {"groupsize" : 32} }' [ --output-pte-path ${MODEL_OUT}/${MODEL_NAME}_gptq.pte | ...dso... ]
```
Now you can run your model with the same command as before:

Expand Down