-
Notifications
You must be signed in to change notification settings - Fork 607
Adding Tiled 2D and 3D Quantizer Linear Base Implementation #5492
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5492
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit daa1c0f with merge base ab628cc ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D61309097 |
This pull request was exported from Phabricator. Differential Revision: D61309097 |
…5492) Summary: Pull Request resolved: pytorch#5492 Adding Tiled Implementation of Weight-Only Quantized Linear operator This diff adds Texture Implementation, will add Buffer impl next. # Diff Stack 1. Add Tiled Implementation of Weight-Only Quantized Linear 2. Add Optimized Quantized Linear Shader and code to invoke shader from Quantized Linear CPP operator 3. [Will Not Land] Use Optimized Quantized Linear implementation Differential Revision: D61309097
40fe2e7
to
2510321
Compare
This pull request was exported from Phabricator. Differential Revision: D61309097 |
…5492) Summary: Pull Request resolved: pytorch#5492 Adding Tiled Implementation of Weight-Only Quantized Linear operator This diff adds Texture Implementation, will add Buffer impl next. # Diff Stack 1. Add Tiled Implementation of Weight-Only Quantized Linear 2. Add Optimized Quantized Linear Shader and code to invoke shader from Quantized Linear CPP operator 3. [Will Not Land] Use Optimized Quantized Linear implementation Differential Revision: D61309097
2510321
to
f8c5a60
Compare
f8c5a60
to
64def59
Compare
…#5492) Summary: Removes q_linear.h and moves implementation directly to q_8w_linear.glsl Reviewed By: nathanaelsee Differential Revision: D61309097
This pull request was exported from Phabricator. Differential Revision: D61309097 |
64def59
to
082c823
Compare
…#5492) Summary: Removes q_linear.h and moves implementation directly to q_8w_linear.glsl Reviewed By: nathanaelsee Differential Revision: D61309097
This pull request was exported from Phabricator. Differential Revision: D61309097 |
…#5492) Summary: Removes q_linear.h and moves implementation directly to q_8w_linear.glsl Reviewed By: nathanaelsee Differential Revision: D61309097
082c823
to
9ae4ee8
Compare
This pull request was exported from Phabricator. Differential Revision: D61309097 |
…#5492) Summary: Removes q_linear.h and moves implementation directly to q_8w_linear.glsl Reviewed By: nathanaelsee Differential Revision: D61309097
9ae4ee8
to
daa1c0f
Compare
This pull request was exported from Phabricator. Differential Revision: D61309097 |
This pull request has been merged in 8f6c16e. |
Summary: The function defs used to live in a separate header file before D61309097 (pytorch#5492), but were moved to the shader file directly to mirror a similar refactoring for the fp linear shader. It's easier to reason about the shader without having to jump back and forth from the minimal main() functions to the q_8w_linear functions. Differential Revision: D70127663
Summary:
Adding Tiled Implementation of Weight-Only Quantized Linear operator
This diff adds Texture Implementation, will add Buffer impl next.
Diff Stack
Differential Revision: D61309097