4 commits

Author	SHA1	Message	Date
Jiajia Qin	fffefb1c22	[js/webgpu] Optimize matmul (#16969) ... ### Description Changes in this PR: 1) use the optimized version `makeMatMulPacked[Vec4]Source` to support matmul. 2) enable the conv2dByMatMul path. 3) support broadcast 4) use IndicesHelper. MatMul with M = 512, K = 512, N = 512 becomes 2ms from 15ms when enabling profilingMode on my ADL.	2023-08-29 12:40:57 -07:00
Yulong Wang	1743e9a615	[js] enable formatter for more file types (#16888) ... ### Description enable formatter for .js/.json/.jsonc/.md files	2023-07-28 15:46:58 -07:00
Yulong Wang	3e8cabbc3e	[js/web] WebGL backend refactor (#8586)	2021-08-12 12:30:49 -07:00
Yulong Wang	4ebc9c3b5e	[JS] onnxruntime-web (#7394) ... * add web * add script and test * fix lint * add test/data/ops * add test/data/node/ to gitignore * modify scripts * add onnxjs * fix tests * fix test-runner * fix sourcemap * fix onnxjs profiling * update test list * update README * resolve comments * set wasm as default backend * rename package * update copyright header * do not use class "Buffer" in browser context * revise readme	2021-04-27 00:04:25 -07:00