Group Gemm Baseline

[gzy19990617]

Hello, is it compared with this cutlass example?

https://github.com/NVIDIA/cutlass/tree/main/examples/57_hopper_grouped_gemm

Or can provide a baseline? Thanks a lot！

[LyricZhao]

Hello, is it compared with this cutlass example?

No, it is compared to our internal impls with CUTLASS.

Or can provide a baseline? Thanks a lot！

Sorry, we cannot share internal modified CUTLASS impls currently.

[gzy19990617]

Hello, is it compared with this cutlass example?

No, it is compared to our internal impls with CUTLASS.

Or can provide a baseline? Thanks a lot！

Sorry, we cannot share internal modified CUTLASS impls currently.

OK, thanks❤️

[LinHR000]

Hello, is it compared with this cutlass example?

No, it is compared to our internal impls with CUTLASS.

Or can provide a baseline? Thanks a lot！

Sorry, we cannot share internal modified CUTLASS impls currently.

internal bench also fp8 implementation, right?

[xuzhean]

Hello, is it compared with this cutlass example?

No, it is compared to our internal impls with CUTLASS.

Or can provide a baseline? Thanks a lot！

Sorry, we cannot share internal modified CUTLASS impls currently.

internal bench also fp8 implementation, right?

yes