Define warmup allocator for torchao quantization #37764
Open
+39
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the |
SunMarc
approved these changes
Apr 24, 2025
Comment on lines
281
to
285
| """ | ||
| The factor to be used in `caching_allocator_warmup` to get the number of bytes to pre-allocate to warm up cuda. | ||
| A factor of 2 means we allocate all bytes in the empty model (since we allocate in fp16), a factor of 4 means | ||
| we allocate half the memory of the weights residing in the empty model, etc... | ||
| """ |
There was a problem hiding this comment.
maybe explain a bit why we need to change for torchao
Comment on lines
289
to
290
| quant_type = self.quantization_config.quant_type | ||
| if isinstance(quant_type, AOBaseConfig): |
There was a problem hiding this comment.
add a small comment for autoquant
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Since when computing the total number of bytes of a torchao quantized model using :
param_byte_count = param.numel() * param.element_size()theparam.element_size()is not correct, we need to account for that and have a factor of 4 forint8models and a factor of8forint4models