Skip to content

[fmhav2] request for preparation phase kernel #3254

@jimmyzho

Description

@jimmyzho

FlashInfer fmha_v2 API has some flaws: it introduces some tiny H2Ds or tiny cuda kernels that cause the perf to drop. Although there has been some effort reduce this, in TRTLLM, these preparation steps are all fused into a kernel that runs before the FMHA kernel itself. We might need to do something similar to get the best performance here.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    Status

    Todo

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions