-
Notifications
You must be signed in to change notification settings - Fork 646
[Backend Tester] Add additional quantized test flows for XNNPACK and Vulkan #13534
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13534
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 106 PendingAs of commit 9e604b4 with merge base 07b0883 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
flow: [ | ||
qnn, qnn_16a16w, qnn_16a8w, qnn_16a4w, qnn_16a4w_block, qnn_8a8w, | ||
vulkan, vulkan_static_int8_per_channel, | ||
xnnpack, xnnpack_dynamic_int8_per_channel, xnnpack_static_int8_per_channel, xnnpack_static_int8_per_tensor |
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.
no groupwise 4b? I am ok for now, just checking if you run into something or just low prio for now.
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.
Yeah, I intend to add that. I was planning to confirm with @metascroy which AO API is recommended and update the XNNPACK delegate docs, as well.
Wire up the PT2E Vulkan quantizer and add additional test flows for XNNPACK PT2E (8-bit static per-tensor and 8-bit dynamic per-channel).
cc @SS-JIA @manuelcandales @cbilgin