204-pull-base-binaries-from-gh-releases-for-encoderfile-builds - Branch - mozilla-ai/encoderfile

feat(build): pull base binaries from gh releases for encoderfile builds

#213Merged

Comparing

204-pull-base-binaries-from-gh-releases-for-encoderfile-builds

(

69f7c4d

) with

main

(

8757a98

)

Untouched: 20

Skipped: 20

Benchmarks

40 total

sequence_classification_postprocess[16]

encoderfile-core/benches/postprocessing.rs

+2%

32.3 µs31.8 µs

sequence_classification_postprocess[64]

encoderfile-core/benches/postprocessing.rs

48.3 µs48.1 µs

bench_seq_cls_softmax[(32, 8)]

encoderfile-core/benches/benchmark_transforms.rs

148 µs147.6 µs

bench_tok_cls_softmax[(16, 16, 2)]

encoderfile-core/benches/benchmark_transforms.rs

184.4 µs184.1 µs

bench_seq_cls_softmax[(128, 32)]

encoderfile-core/benches/benchmark_transforms.rs

293.3 µs293 µs

token_classification_postprocess[(8, 16)]

encoderfile-core/benches/postprocessing.rs

3.6 ms3.6 ms

token_classification_postprocess[(64, 512)]

encoderfile-core/benches/postprocessing.rs

61.3 ms61.2 ms

embedding_postprocess[(8, 16, 384)]

encoderfile-core/benches/postprocessing.rs

4.6 ms4.6 ms

token_classification_postprocess[(16, 128)]

encoderfile-core/benches/postprocessing.rs

8.2 ms8.2 ms

bench_tok_cls_softmax[(32, 128, 8)]

encoderfile-core/benches/benchmark_transforms.rs

1.8 ms1.8 ms

bench_tok_cls_softmax[(128, 256, 32)]

encoderfile-core/benches/benchmark_transforms.rs

35.7 ms35.7 ms

embedding_postprocess[(16, 128, 768)]

encoderfile-core/benches/postprocessing.rs

25.2 ms25.2 ms

bench_l2_normalize[Axis(1)]

encoderfile-core/benches/l2_norm.rs

3 ms3 ms

bench_embedding_l2_normalization[(32, 128, 384)]

encoderfile-core/benches/benchmark_transforms.rs

65.3 ms65.3 ms

bench_embedding_l2_normalization[(32, 256, 768)]

encoderfile-core/benches/benchmark_transforms.rs

267 ms267 ms

bench_l2_normalize[Axis(0)]

encoderfile-core/benches/l2_norm.rs

1.6 ms1.6 ms

embedding_postprocess[(64, 512, 1024)]

encoderfile-core/benches/postprocessing.rs

312.1 ms312.1 ms

bench_seq_cls_softmax[(16, 2)]

encoderfile-core/benches/benchmark_transforms.rs

137.2 µs137.2 µs

bench_embedding_l2_normalization[(16, 16, 16)]

encoderfile-core/benches/benchmark_transforms.rs

337.3 µs337.5 µs

sequence_classification_postprocess[8]

encoderfile-core/benches/postprocessing.rs

-2%

10.9 µs11.1 µs

The benchmarks below 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*

Commits

Click on a commit to change the comparison range

Base

main

8757a98

-0.25%

fmt

62b899c

3 months ago

by besaleli

+0.26%

lint

6d162df

3 months ago

by besaleli

+0.04%

fix tests

69f7c4d

3 months ago

by besaleli

Home Terms Privacy Docs