Add AffineQuantizedTensor based workflow doc and examples
#277
Conversation
This file contains 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/277
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit accdb3d with merge base 6dd63b8 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
msaroufim
reviewed
May 25, 2024
torchao/quantization/README.md
Outdated
|
|
||
|
|
||
| # benchmark to see the speedup | ||
| from torch.utils.benchmark import Timer |
There was a problem hiding this comment.
We have a benchmark util now https://github.com/pytorch/ao/blob/main/torchao/utils.py#L4
Mind if we update it in case yours is subtly different?
There was a problem hiding this comment.
sure, but we probably need to follow up and enable benchmark for cpu and mps as well for that, created an issue here: #287
msaroufim
reviewed
May 25, 2024
msaroufim
reviewed
May 25, 2024
msaroufim
reviewed
May 25, 2024
torchao/quantization/README.md
Outdated
| # optional filtering for module name, shape etc. | ||
| # quantization activation (needed by dynamic quantization) | ||
| # m.weight = nn.Parameter(to_laq(m.weight, device=..., layout=..., ...)) | ||
| m.weight = nn.Parameter(to_aq(m.weight, device=..., layout=..., ...)) |
There was a problem hiding this comment.
Can we make this a real snippet people can copy paste?
msaroufim
requested changes
May 25, 2024
Summary: att Test Plan: . Reviewers: Subscribers: Tasks: Tags:
msaroufim
approved these changes
May 29, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
Add special case for zero-temperature sampling. For stories15M on my devserver, seems to improve tokens/sec as follows: before: 189, 180, 166 after: 264, 285, 285
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.
Summary:
att
Test Plan:
.
Reviewers:
Subscribers:
Tasks:
Tags: