Fused quant linear kernel (#19490)#19490
Open
DrJessop wants to merge 3 commits into
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19490
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ⏳ 8 Pending, 2 Unrelated FailuresAs of commit c987558 with merge base 8020fe0 ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@DrJessop has exported this pull request. If you are a Meta employee, you can view the originating Diff in D103754853. |
This PR needs a
|
aliafzal
approved these changes
May 11, 2026
meta-codesync
Bot
changed the title
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
May 12, 2026
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
DrJessop
force-pushed
the
export-D103754853
branch
from
c57549a to
1d27ab1
Compare
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
May 12, 2026
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
May 12, 2026
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
May 12, 2026
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
added 3 commits
May 12, 2026 10:07
Summary: Fused quant hardswish kernel with optional dequantize/quantize. Unary op that applies x * min(max(x+3, 0), 6) / 6. Supports per-tensor and per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754780
Summary: Fused quant batch matrix multiply kernel with optional dequantize/quantize. Binary op on 3D tensors [B,M,K] x [B,K,N] -> [B,M,N]. Supports per-tensor and per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754815
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
DrJessop
force-pushed
the
export-D103754853
branch
from
1d27ab1 to
c987558
Compare
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
May 12, 2026
Summary: Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization. Reviewed By: mvartani-meta Differential Revision: D103754853
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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:
Fused quant linear kernel (out = inp @ weight^T + bias) with optional dequantize/quantize. Supports 4 sets of qparams (inp, weight, bias, out), optional bias, and per-tensor/per-channel quantization.
Reviewed By: mvartani-meta
Differential Revision: D103754853