Add floating point options for autoquant and add accuracy measurement #1355
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
Summary: * This PR adds float32/float16/bfloat16 as a list of options for autoquant, it converts input/weight/bias/output to the specified dtype * Also adds min_sqnr (https://en.wikipedia.org/wiki/Signal-to-quantization-noise_ratio) to allow users to filter out the quantization methods that has large numerical impact compared to original output Note that we use random generated input activation right now, we can improve this by adding the support for using real inputs Test Plan: python generate.py --checkpoint_path $CHECKPOINT_PATH/$MODEL_REPO/model.pth --compile --compile_prefill --quantization autoquant-fp Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1355
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b1ced92 with merge base 478d15b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
added
the
topic: improvement
cpuhrsch
approved these changes
Nov 27, 2024
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Outdated suggestions cannot be applied.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:
Note that we use random generated input activation right now, we can improve this by adding the support for using real inputs
Test Plan:
python generate.py --checkpoint_path $CHECKPOINT_PATH/$MODEL_REPO/model.pth --compile --compile_prefill --quantization autoquant-fp
Reviewers:
Subscribers:
Tasks:
Tags: