This repository was archived by the owner on Sep 10, 2025. It is now read-only.
Deprecating Int8DynActInt4WeightQuantizer #1332
Closed
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
Summary:
Added torchao API int8_dynamic_activation_int4_weight
I ran some benchmark with eager mode and there was some accuracy loss and some slowdowns in compile.
But later I found we only care about performance on executorch. So was trying to benchmark et perf and accuracy. but I can't get the env setup correctly for executorch to run the experiments
Specifically there were some issues when I'm trying to run the following after I installed executorch from pip
```
python3 torchchat.py export llama3.1 --quantize torchchat/quant_config/mobile.json --output-pte-path llama3.1.pte
```
Error:
```
Traceback (most recent call last):
File "/data/users/jerryzh/torchchat/torchchat.py", line 17, in <module>
from torchchat.cli.cli import (
File "/data/users/jerryzh/torchchat/torchchat/cli/cli.py", line 14, in <module>
import torch
File "/home/jerryzh/.conda/envs/torchchat/lib/python3.10/site-packages/torch/__init__.py", line 368, in <module>
from torch._C import * # noqa: F403
ImportError: /home/jerryzh/.conda/envs/torchchat/lib/python3.10/site-packages/torch/lib/../../nvidia/cusparse/lib/libcusparse.so.12: undefined symbol: __nvJitLinkComplete_12_4, version libnvJitLink.so.12
```
Test Plan:
test instruction from Jack: https://docs.google.com/document/d/1eRAoY1Jq4SR5A7iAYC71maSZAPzsBJmr9VuZPhR5ZYA/edit?tab=t.0#bookmark=id.otk3jomaciya
Reviewers:
Subscribers:
Tasks:
Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1332
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
|
@vmpuri jic you missed this |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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:
Added torchao API int8_dynamic_activation_int4_weight I ran some benchmark with eager mode and there was some accuracy loss and some slowdowns in compile.
But later I found we only care about performance on executorch. So was trying to benchmark et perf and accuracy. but I can't get the env setup correctly for executorch to run the experiments
Specifically there were some issues when I'm trying to run the following after I installed executorch from pip
Error:
Test Plan:
test instruction from Jack: https://docs.google.com/document/d/1eRAoY1Jq4SR5A7iAYC71maSZAPzsBJmr9VuZPhR5ZYA/edit?tab=t.0#bookmark=id.otk3jomaciya
Reviewers:
Subscribers:
Tasks:
Tags: