openvino
openvino copied to clipboard
Yi3/fix perf wenet
Details:
- Improve performance for dynamic shape model such as
Wenet - Implement
Concatkernel to avoid frequent oneDNN kernel construction - Implement shape_infer for
Cocant&Transpose - Use shape_infer for
Eltwiserather than self-implementation - Simplify
MatMulkey formulation
Tickets:
- 86353
@a-sidorova , could you please review?
@a-sidorova, could you please take a look once again?
Hi @a-sidorova I think the trial for matmul key improvement is not mature enough and decide to drop that part so that we could focus on the implementation of concat kernel.
@zhangYiIntel also I'd like to suggest you to rebase the branch to the master
@dmitry-gorokhov Could you help review this PR finally ?
@maxnick Could you help review again ?