Update QAT README.md #2162
Update QAT README.md #2162
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2162
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
cc @andrewor14 |
| quantize_( | ||
| m, | ||
| IntXQuantizationAwareTrainingConfig(weight_config=weight_config), | ||
| filter_fn=lambda m, _: isinstance(m, torch.nn.Embedding), | ||
| filter_fn=lambda m, _: isinstance(m, torch.nn.Embedding) or _is_linear(m), |
There was a problem hiding this comment.
Actually this is only if you want to use the same configuration for embedding and linear. I kept them as two separate calls because in the above example linear additionally has activation quantization.
There was a problem hiding this comment.
Yeah you're right and this example won't work if you try and apply a config with activation quantization to both linear and embedding layers at the same time.
You can stack calls to quantize right? Would the right way to go about this two quantize calls, one which iflters for linear, then another which filters for embeddings?
There was a problem hiding this comment.
Yeah if you have slightly different quantization configurations for embedding and linear the right way would be two separate quantize_ calls. This is by design because we don't want to complicate quantize_ to accept a dictionary of configs
Closes #2155.