- 
                Notifications
    You must be signed in to change notification settings 
- Fork 248
Add new torchao experimental a8wxdq for fast ARM CPU quantization #1145
Conversation
| 🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1145
 Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 2 Cancelled Jobs, 1 Unrelated FailureAs of commit d0d87cb with merge base 75b877a ( NEW FAILURES - The following jobs have failed:
 
 CANCELLED JOBS - The following jobs were cancelled. Please retry:
 
 FLAKY - The following job failed but was likely due to flakiness present on trunk:
 
 This comment was automatically generated by Dr. CI and updates every 15 minutes. | 
| @@ -0,0 +1 @@ | |||
| 3fa38aaf1276e36845a82fb399e5054718a441c4 | |||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
TODO: update to commit hash that contains D62394341 after it lands.
| echo $pwd | ||
|  | ||
| cp -R /Users/scroy/fbsource/fbcode/pytorch/ao . | ||
| # git clone https://github.com/pytorch/ao.git | 
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
TODO: remove cp and uncomment clone lines before landing.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
in the meantime I'd recommend replacing /Users/scroy/ with ${HOME}
| endif() | ||
|  | ||
| if(LINK_TORCHAO_CUSTOM_OPS) | ||
| # target_link_libraries(et_run PRIVATE "${TORCHCHAT_ROOT}/torchao-build/cmake-out/lib/liblinear_a8wxdq_EXECUTORCH${CMAKE_SHARED_LIBRARY_SUFFIX}") | 
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Uncomment this line to test with dylib (poor perf vs. static lib)
This adds new torchao experimental a8wxdq for fast ARM CPU quantization.