Skip to content

[float8] Allow specifying arbitrary dtype for each tensor #3057

[float8] Allow specifying arbitrary dtype for each tensor

[float8] Allow specifying arbitrary dtype for each tensor #3057

Annotations

4 errors

test (SM-89, linux.g6.4xlarge.experimental.nvidia.gpu, --pre torch --index-url https://download.p...  /  linux-job

failed Dec 4, 2024 in 59s