Skip to content

Support logits_soft_cap parameter in paged_attention #9387

Support logits_soft_cap parameter in paged_attention

Support logits_soft_cap parameter in paged_attention #9387

Triggered via pull request July 17, 2024 06:52
Status Success
Total duration 1h 19m 32s
Artifacts 5

build_and_test.yml

on: pull_request
get-torch-commit
2s
get-torch-commit
Build XLA CUDA plugin  /  build
2m 27s
Build XLA CUDA plugin / build
Build PyTorch/XLA  /  build
23m 9s
Build PyTorch/XLA / build
Build PyTorch with CUDA  /  build
21m 14s
Build PyTorch with CUDA / build
Build docs  /  build-docs
1m 26s
Build docs / build-docs
TPU tests  /  tpu-test
TPU tests / tpu-test
Matrix: GPU tests / test
Matrix: CPU tests / test
Matrix: GPU tests requiring torch CUDA / test
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size
cpp-test-bin
664 MB
cuda-plugin
115 MB
github-pages
4.25 MB
torch-with-cuda
339 MB
torch-xla-wheels
210 MB