openvino
openvino copied to clipboard
Yi3/fix perf wenet
Details:
-
Improve performance for dynamic shape model such as
Wenet
-
Implement
Concat
kernel to avoid frequent oneDNN kernel construction -
Implement shape_infer for
Cocant
&Transpose
-
Use shape_infer for
Eltwise
rather than self-implementation -
Simplify
MatMul
key 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 ?