Jiajia Qin abdf8b7c3f [js/webgpu] Optimize broadcast binary. (#18185) ... ### Description Currently, the binary algorithms are divided into the vectorize one (efficient) and non-vectorize one (less efficient). Below situations will go to the vectorize one: 1) A or B's shape length is 1. 2) The shared dimensions length of A and B are divisible by 4. 3) A and B have same shape. This PR adds another situation as below to go to the vectorize algorithm. 4. A or B's last dimension is divisible by 4. With this change, the aggerate time of Add in sam-b-encoder becomes 309.65 ms from 409.12 ms on Intel ADL.		2023-11-20 16:52:17 -08:00
..
onnxjs	[js] optimize eslint config (#18460)	2023-11-20 12:00:56 -08:00
wasm	[js/webgpu] Optimize broadcast binary. (#18185)	2023-11-20 16:52:17 -08:00
backend-onnxjs.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
backend-wasm-inference.ts	Add "glue" between training WASM artifacts and training web (#17474)	2023-10-12 11:16:56 -07:00
backend-wasm-training.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
backend-wasm.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
build-def.d.ts	[js/web] fix typescript type check (#18343)	2023-11-10 16:03:38 -08:00
index.ts	[js/web] fix a few package consuming problems (#18109)	2023-10-30 08:11:43 -07:00
version.ts