Skip to content
Python package

Support LLM.int8() inference with torch.compile (#1594) #1231

Sign in to view logs

Support LLM.int8() inference with torch.compile (#1594)

Support LLM.int8() inference with torch.compile (#1594) #1231

Re-run triggered April 17, 2025 21:59
@matthewdouglasmatthewdouglas
97073cd
main
Status Success
Total duration 7m 26s
Artifacts 28

python-package.yml

on: push
Matrix: build-shared-libs-cuda
Matrix: build-shared-libs
Matrix: build-wheels
audit-wheels
10s
audit-wheels
Create release and upload artifacts
12s
Create release and upload artifacts
Publish wheels to PyPI
0s
Publish wheels to PyPI
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size Digest
bdist_wheel_macos-latest_aarch64 Expired
93 KB
sha256:b657b541192964c3d9367d7bf21147229490ee7f9c2f3f0f9870871eb0167b15
bdist_wheel_macos-latest_x86_64 Expired
93 KB
sha256:dcc72155e41796697253ee336f788a63e088ce6b34cd351aec6f71c517bb72b1
bdist_wheel_ubuntu-22.04_x86_64 Expired
69.9 MB
sha256:bc65a767e9f6b896a20c4ef92a806fa383d5f604d206473621153d9490e7205c
bdist_wheel_windows-latest_x86_64 Expired
69.3 MB
sha256:1112b572bba8b8782b35996cbe03c5b6c1a37c59d3a6ccd0b9c62a200e534f8f
shared_library_cuda_ubuntu-22.04_x86_64_11.7.1 Expired
6.19 MB
sha256:06b9265036d9db83790fd1e884f389c10c0e715f1bbfe4041942630d00fe6edf
shared_library_cuda_ubuntu-22.04_x86_64_12.0.1 Expired
7.27 MB
sha256:4fb7cf40f007afc9ed4d63c6ddbce9d0ecbb0fe0a3f684c71eb300848f677d54
shared_library_cuda_ubuntu-22.04_x86_64_12.4.1 Expired
7.27 MB
sha256:4d861a7376f2b4562830184a3b047c6f1fc80058f57f65c267937f7ac67c1bb3
shared_library_cuda_ubuntu-22.04_x86_64_12.5.1 Expired
7.29 MB
sha256:66db48d1fc7201a0e767583859d3df825e617fd19b69f2ce5fbecf525855ba9a
shared_library_cuda_ubuntu-22.04_x86_64_12.8.1 Expired
5.89 MB
sha256:5e4dcb7ec96a69909bf05c26763177c173ba975a7e17c448acf6967c08dbbc71
⚡