Skip to content
MacOS CI Pipeline

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #20665

Sign in to view logs

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #20665

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Objective-C-StaticAnalysis
3m 1s
iphone_simulator (x86_64)
36m 11s
iphone_simulator (arm64)
52m 36s
xnnpack / build-and-test (arm64, arm64, Debug)
59m 58s
coreml / build-and-test (arm64, arm64, Release)
1h 43m 14s
webgpu / build-and-test (arm64, x86_64, Release)
51m 14s
webgpu / build-and-test (arm64, arm64, Debug)
1h 13m 48s
coreml / build-and-test (arm64, arm64, Debug)
58m 39s
cpu / build-and-test (arm64, arm64, Release)
44m 36s
webgpu / build-and-test (arm64, arm64, Release)
59m 20s
coreml / build-and-test (arm64, x86_64, Release)
40m 43s
cpu / build-and-test (arm64, arm64, Debug)
49m 49s
10h 33m 9s