-
Notifications
You must be signed in to change notification settings - Fork 741
Using generic implementation for 16-bit activations and 8-bit weights for matmul in backends #16008
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
Open
RahulC7
wants to merge
3
commits into
pytorch:main
Choose a base branch
from
RahulC7:export-D87997149
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+725
−11
Open
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
| Original file line number | Diff line number | Diff line change | ||||||
|---|---|---|---|---|---|---|---|---|
|
|
@@ -10,6 +10,7 @@ | |||||||
| #include <executorch/backends/cadence/hifi/operators/operators.h> | ||||||||
| #include <executorch/runtime/kernel/kernel_includes.h> | ||||||||
| #include <xa_nnlib_kernels_api.h> | ||||||||
| #include <on_device_ai/Assistant/Jarvis/min_runtime/operators/generic/op_quantized_linear.h> | ||||||||
| #include <xtensa/tie/xt_datacache.h> | ||||||||
| #include <algorithm> | ||||||||
| #include <cmath> | ||||||||
|
|
@@ -218,7 +219,24 @@ void quantized_linear_out( | |||||||
| int64_t out_zero_point, | ||||||||
| __ET_UNUSED const optional<Tensor>& offset, | ||||||||
| Tensor& out) { | ||||||||
| if (out.scalar_type() == executorch::aten::ScalarType::Byte) { | ||||||||
|
|
||||||||
| if (out.scalar_type() == ::executorch::aten::ScalarType::Short && | ||||||||
| in.scalar_type() == ::executorch::aten::ScalarType::Short && | ||||||||
| weight.scalar_type() == ::executorch::aten::ScalarType::Char) { | ||||||||
| ::impl::generic::native::quantized_linear_out( | ||||||||
| ctx, | ||||||||
| in, | ||||||||
| weight, | ||||||||
| bias, | ||||||||
| in_zero_point, | ||||||||
| weight_zero_point, | ||||||||
| out_multiplier, | ||||||||
| out_shift, | ||||||||
| out_zero_point, | ||||||||
| offset, | ||||||||
| out); | ||||||||
| } | ||||||||
| else if (out.scalar_type() == executorch::aten::ScalarType::Byte) { | ||||||||
|
Comment on lines
+238
to
+239
|
||||||||
| } | |
| else if (out.scalar_type() == executorch::aten::ScalarType::Byte) { | |
| } else if (out.scalar_type() == executorch::aten::ScalarType::Byte) { |
Comment on lines
+296
to
+297
Copilot
AI
Nov 28, 2025
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.
Missing space after closing brace on line 296. The 'else' should be on the same line as the closing brace of the preceding if block, or there should be consistent formatting with other similar conditionals in the file.
Suggested change
| } | |
| else if (out.scalar_type() == executorch::aten::ScalarType::Byte) { | |
| } else if (out.scalar_type() == executorch::aten::ScalarType::Byte) { |
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| /* | ||
| * Copyright (c) Meta Platforms, Inc. and affiliates. | ||
| * All rights reserved. | ||
| * | ||
| * This source code is licensed under the BSD-style license found in the | ||
| * LICENSE file in the root directory of this source tree. | ||
| */ | ||
|
|
||
| #pragma once | ||
|
|
||
| #include "executorch/runtime/core/exec_aten/exec_aten.h" | ||
| #include "executorch/runtime/kernel/kernel_runtime_context.h" | ||
|
|
||
| namespace impl { | ||
| namespace HiFi { | ||
| namespace native { | ||
|
|
||
| ::executorch::aten::Tensor& quantized_matmul_out( | ||
| ::executorch::runtime::KernelRuntimeContext& ctx, | ||
| const ::executorch::aten::Tensor& X, | ||
| int64_t X_zero_point, | ||
| const ::executorch::aten::Tensor& Y, | ||
| int64_t Y_zero_point, | ||
| const ::executorch::aten::optional<::executorch::aten::Tensor>& bias, | ||
| int64_t out_multiplier, | ||
| int64_t out_shift, | ||
| int64_t out_zero_point, | ||
| bool transposed, | ||
| ::executorch::aten::Tensor& out); | ||
|
|
||
| } // namespace native | ||
| } // namespace HiFi | ||
| } // namespace impl |
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
Oops, something went wrong.
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.
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.
Variable declaration for 'optimized' appears after the early return, but it was previously at the beginning of the function. This creates inconsistent code structure and the variable is now unreachable when the W8A16 path is taken. Consider moving this declaration back before the W8A16 conditional check for consistency with the original code structure.