mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-18 21:21:17 +00:00
d981b153d3
### Description <!-- Describe your changes. --> This PR is a follow-up to https://github.com/microsoft/onnxruntime/pull/23488 and partially improves upon https://github.com/microsoft/onnxruntime/issues/23403. It does the following: - Prevents unnecessary cache shader recompilation for 'nearest' resize operation. - Fixes precision (offset-by-one) errors with asymmetric coordinate transform. When running the Kokoro TTS model, values for the `/decoder/decoder/generator/f0_upsamp/Resize_output_0` results in differences at the end bounds due to precision issues when dividing 21600 by 72 (should be 300, but seemingly results in 299.999, which causes issues when flooring) ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> I did a deep dive over the weekend to try fix Kokoro TTS on WebGPU and found that the above node had a large difference. Thinking this was a major issue, I spent some time fixing it. Turns out, it only happens for a small number of values, leading to high maximum error, but most values are correct (as seen here). BEFORE: ``` [/decoder/decoder/generator/f0_upsamp/Resize_output_0] atol: 78.6640682220459 | rtol: 24.13991587587724 | avgDiff: 0.009967932171121087 | medianDiff: 0.000030517578125 ``` AFTER: ``` [/decoder/decoder/generator/f0_upsamp/Resize_output_0] atol: 0.0011138916015625 | rtol: 0.0020059924232260704 | avgDiff: 0.00008570214675873825 | medianDiff: 0.000030517578125 ``` So, although it has a very small impact on the final output (waveform), this bug could appear with other models in a more severe way. BEFORE: ``` [waveform] atol: 0.04784199967980385 | rtol: 1366.0462001093495 | avgDiff: 0.0009544936942737713 | medianDiff: 0.00015346752479672432 ``` AFTER: ``` [waveform] atol: 0.04775865003466606 | rtol: 1354.7002460360852 | avgDiff: 0.000954830244055033 | medianDiff: 0.00015274062752723694 ``` |
||
|---|---|---|
| .. | ||
| 3rd-party | ||
| argminmax.ts | ||
| attention.ts | ||
| batch-norm.ts | ||
| bias-add.ts | ||
| bias-split-gelu.ts | ||
| binary-op.ts | ||
| common.ts | ||
| concat.ts | ||
| conv-grouped.ts | ||
| conv-transpose.ts | ||
| conv.ts | ||
| cumsum.ts | ||
| depth-to-space.ts | ||
| einsum.ts | ||
| expand.ts | ||
| fast-gelu.ts | ||
| fuse-utils.ts | ||
| gather-block-quantized.ts | ||
| gather-elements.ts | ||
| gather-nd.ts | ||
| gather.ts | ||
| gemm.ts | ||
| grid-sample.ts | ||
| group-query-attention.ts | ||
| instance-norm.ts | ||
| layer-norm.ts | ||
| matmul-shaders.ts | ||
| matmul.ts | ||
| matmulnbits.ts | ||
| multihead-attention.ts | ||
| pad.ts | ||
| pool.ts | ||
| quantize-linear.ts | ||
| range.ts | ||
| reduce-shared.ts | ||
| reduce.ts | ||
| resize.ts | ||
| rotary-embedding.ts | ||
| scatter-nd.ts | ||
| skip-layer-norm.ts | ||
| slice.ts | ||
| softmax.ts | ||
| split.ts | ||
| tile.ts | ||
| transpose.ts | ||
| unary-op.ts | ||
| where.ts | ||