122-validate-transforms-on-compile - Branch - mozilla-ai/encoderfile - CodSpeed

Blog Docs Changelog

feat: validate transforms on compile

Comparing

122-validate-transforms-on-compile

(

32746ca

) with

main

(

ef6c587

)

0%

Untouched: 20

Skipped: 20

Benchmarks

Skipped (20)

These benchmarks were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks

bench_seq_cls_softmax[(128, 32)]

encoderfile/benches/benchmark_transforms.rs

Skipped

269.5 µs*

bench_tok_cls_softmax[(128, 256, 32)]

encoderfile/benches/benchmark_transforms.rs

Skipped

27.9 ms*

bench_embedding_l2_normalization[(32, 256, 768)]

encoderfile/benches/benchmark_transforms.rs

Skipped

266.1 ms*

embedding_postprocess[(64, 512, 1024)]

encoderfile/benches/postprocessing.rs

Skipped

311.3 ms*

bench_embedding_l2_normalization[(32, 128, 384)]

encoderfile/benches/benchmark_transforms.rs

Skipped

65.1 ms*

bench_seq_cls_softmax[(16, 2)]

encoderfile/benches/benchmark_transforms.rs

Skipped

127.5 µs*

bench_embedding_l2_normalization[(16, 16, 16)]

encoderfile/benches/benchmark_transforms.rs

Skipped

337 µs*

embedding_postprocess[(8, 16, 384)]

encoderfile/benches/postprocessing.rs

Skipped

4.6 ms*

bench_seq_cls_softmax[(32, 8)]

encoderfile/benches/benchmark_transforms.rs

Skipped

134.7 µs*

sequence_classification_postprocess[16]

encoderfile/benches/postprocessing.rs

Skipped

33.6 µs*

embedding_postprocess[(16, 128, 768)]

encoderfile/benches/postprocessing.rs

Skipped

25.2 ms*

bench_tok_cls_softmax[(32, 128, 8)]

encoderfile/benches/benchmark_transforms.rs

Skipped

1.4 ms*

bench_tok_cls_softmax[(16, 16, 2)]

encoderfile/benches/benchmark_transforms.rs

Skipped

149.2 µs*

bench_l2_normalize[Axis(0)]

encoderfile/benches/l2_norm.rs

Skipped

1.5 ms*

sequence_classification_postprocess[64]

encoderfile/benches/postprocessing.rs

Skipped

47.8 µs*

token_classification_postprocess[(8, 16)]

encoderfile/benches/postprocessing.rs

Skipped

3.6 ms*

token_classification_postprocess[(64, 512)]

encoderfile/benches/postprocessing.rs

Skipped

61.2 ms*

sequence_classification_postprocess[8]

encoderfile/benches/postprocessing.rs

Skipped

11 µs*

token_classification_postprocess[(16, 128)]

encoderfile/benches/postprocessing.rs

Skipped

8.2 ms*

bench_l2_normalize[Axis(1)]

encoderfile/benches/l2_norm.rs

Skipped

3 ms*

Passed

sequence_classification_postprocess[16]

encoderfile-core/benches/postprocessing.rs

+3%

32.9 µs32 µs

bench_tok_cls_softmax[(32, 128, 8)]

encoderfile-core/benches/benchmark_transforms.rs

+2%

1.8 ms1.8 ms

bench_tok_cls_softmax[(16, 16, 2)]

encoderfile-core/benches/benchmark_transforms.rs

+1%

184.8 µs182.6 µs

bench_tok_cls_softmax[(128, 256, 32)]

encoderfile-core/benches/benchmark_transforms.rs

+1%

35.7 ms35.4 ms

bench_seq_cls_softmax[(128, 32)]

encoderfile-core/benches/benchmark_transforms.rs

0%

292.3 µs291.2 µs

bench_seq_cls_softmax[(16, 2)]

encoderfile-core/benches/benchmark_transforms.rs

0%

137 µs136.6 µs

token_classification_postprocess[(64, 512)]

encoderfile-core/benches/postprocessing.rs

0%

61.3 ms61.2 ms

token_classification_postprocess[(16, 128)]

encoderfile-core/benches/postprocessing.rs

0%

8.2 ms8.2 ms

token_classification_postprocess[(8, 16)]

encoderfile-core/benches/postprocessing.rs

0%

3.6 ms3.6 ms

bench_l2_normalize[Axis(0)]

encoderfile-core/benches/l2_norm.rs

0%

1.5 ms1.5 ms

bench_embedding_l2_normalization[(32, 128, 384)]

encoderfile-core/benches/benchmark_transforms.rs

0%

65.1 ms65.1 ms

embedding_postprocess[(64, 512, 1024)]

encoderfile-core/benches/postprocessing.rs

0%

312 ms312 ms

bench_embedding_l2_normalization[(32, 256, 768)]

encoderfile-core/benches/benchmark_transforms.rs

0%

266.1 ms266.1 ms

bench_l2_normalize[Axis(1)]

encoderfile-core/benches/l2_norm.rs

0%

3 ms3 ms

bench_embedding_l2_normalization[(16, 16, 16)]

encoderfile-core/benches/benchmark_transforms.rs

0%

337.4 µs337.4 µs

embedding_postprocess[(16, 128, 768)]

encoderfile-core/benches/postprocessing.rs

0%

25.2 ms25.2 ms

bench_seq_cls_softmax[(32, 8)]

encoderfile-core/benches/benchmark_transforms.rs

0%

146.7 µs146.7 µs

embedding_postprocess[(8, 16, 384)]

encoderfile-core/benches/postprocessing.rs

0%

4.6 ms4.6 ms

sequence_classification_postprocess[64]

encoderfile-core/benches/postprocessing.rs

0%

47.9 µs48 µs

sequence_classification_postprocess[8]

encoderfile-core/benches/postprocessing.rs

-1%

11 µs11.1 µs

Commits

Click on a commit to change the comparison range

Base

main

ef6c587

+0.08%

update

e157b8e

1 day ago

by besaleli

+0.26%

clippy

32746ca

1 day ago

by besaleli

© 2025 CodSpeed Technology

Home Terms Privacy Docs