Skip to content
Build Presets

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #35822

Sign in to view logs

[cuda backend] optimized L_kv threshold for sdpa implementation selection.

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #35822

Run time

Learn about OS pricing on GitHub Actions
Job Run time
windows (pybind) / build
20m 0s
linux (pybind, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build
7m 32s
linux (pybind, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build
8m 40s
linux (linux, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build
7m 29s
apple (ios) / build
8m 10s
apple (macos) / build
8m 38s
zephyr (zephyr) / build
10m 42s
windows (windows) / build
16m 39s
apple (ios-simulator) / build
8m 33s
apple (profiling) / build
6m 8s
apple (llm) / build
6m 40s
linux (linux, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build
8m 21s
linux (llm, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build
7m 36s
apple (pybind) / build
7m 50s
linux (llm, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build
8m 22s
2h 21m 20s