Fused quant linear kernel (#19490)#19490
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: ❌ 39 New Failures, 2 Unrelated FailuresAs of commit 5bf8d39 with merge base 7cd209d ( NEW FAILURES - The following jobs have failed:
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. |
|
@DrJessop has exported this pull request. If you are a Meta employee, you can view the originating Diff in D103754853. |
This PR needs a
|
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
c57549a to
1d27ab1
Compare
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
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
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
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
1d27ab1 to
c987558
Compare
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
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
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
c987558 to
5bf8d39
Compare
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