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

Skipped (20)

Passed

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

Commits

Click on a commit to change the comparison range

Base

main

8757a98

-0.25%

fmt

62b899c

5 days ago

by besaleli

+0.26%

lint

6d162df

5 days ago

by besaleli

+0.04%

fix tests

69f7c4d

5 days ago

by besaleli

Home Terms Privacy Docs