Skip to content

Implement dual LUT scheme for int16 reciprocal/rsqrt operations #3773

Implement dual LUT scheme for int16 reciprocal/rsqrt operations

Implement dual LUT scheme for int16 reciprocal/rsqrt operations #3773

Triggered via pull request December 25, 2025 18:50
Status Success
Total duration 23m 0s
Artifacts 3

metal.yml

on: pull_request
Matrix: export-model-metal-artifact
test-executorch-metal-build  /  macos-job
6m 10s
test-executorch-metal-build / macos-job
Matrix: test-model-metal-e2e
Fit to window
Zoom out
Zoom in

Annotations

6 errors
test-model-metal-e2e (openai, whisper-large-v3-turbo, non-quantized) / macos-job
clone of 'https://gitlab.com/libeigen/eigen.git' into submodule path '/Users/ec2-user/runner/_work/executorch/executorch/pytorch/executorch/kernels/optimized/third-party/eigen' failed
test-model-metal-e2e (openai, whisper-large-v3-turbo, non-quantized) / macos-job
remote error: GitLab is currently unable to handle this request due to load (ID 9b3a9b2825d5d6c8-IAD).
test-model-metal-e2e (openai, whisper-small, non-quantized) / macos-job
clone of 'https://gitlab.com/libeigen/eigen.git' into submodule path '/Users/ec2-user/runner/_work/executorch/executorch/pytorch/executorch/kernels/optimized/third-party/eigen' failed
test-model-metal-e2e (openai, whisper-small, non-quantized) / macos-job
remote error: GitLab is currently unable to handle this request due to load (ID 9b3a9b0b5317081e-IAD).
test-model-metal-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job
clone of 'https://gitlab.com/libeigen/eigen.git' into submodule path '/Users/ec2-user/runner/_work/executorch/executorch/pytorch/executorch/kernels/optimized/third-party/eigen' failed
test-model-metal-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job
remote error: GitLab is currently unable to handle this request due to load (ID 9b3a9b2aa7522421-IAD).

Artifacts

Produced during runtime
Name Size Digest
mistralai-Voxtral-Mini-3B-2507-metal-non-quantized
6.82 GB
sha256:f14ff25c50d29c2d680087dbbf98222799fcd27b863b01799802064aea7af618
openai-whisper-large-v3-turbo-metal-non-quantized
1.18 GB
sha256:0ed7d8d23a9f97bf63227a2f74ff6310bdb9f2c736cd3455e62bcaea47086aec
openai-whisper-small-metal-non-quantized
361 MB
sha256:4c370215eebe64368b86d3d0ed93faae3a05f9e1636ed24256d02c692fa30698