Jiajia Qin 7be006c466 [js/webgpu] Optimize convtranspose (#23302) ... ### Description <!-- Describe your changes. --> BUG #23273 With this change, I see the convTranspose time in that bug becomes ~7s from ~90s on my Meteor Lake. This PR does below things: 1. Use stride to update the increasement in the loop. In the bug, the stride is 1024, which can greatly reduce the loop times. 2. Support components for A to reduce the memory access times. 3. When output channels is 1, the b components can be same with A to further reduce the memory access times.		2025-01-09 11:24:42 -08:00
..
data/ops	[js/webgpu] Optimize convtranspose (#23302)	2025-01-09 11:24:42 -08:00
e2e	[js/web] fix package export for bundlers (#23257)	2025-01-09 11:01:00 -08:00
unittests	[js] change default formatter for JavaScript/TypeScript from clang-format to Prettier (#21728)	2024-08-14 16:51:22 -07:00
op-test-schema.json	[js/web] Add support for int4/uint4 tensor (#21720)	2024-08-15 21:32:10 -07:00
suite-test-list.jsonc	[js/webgpu] Add GatherND (#22847)	2024-12-04 09:57:32 -08:00
test-main.ts	[js/webgpu] Manage model download with a specific unittest option (#22214)	2024-09-30 18:27:43 -07:00
test-runner.ts	[js/web] Update API for ort.env.webgpu (#23026)	2024-12-11 10:24:14 -08:00
test-shared.ts	[js] change default formatter for JavaScript/TypeScript from clang-format to Prettier (#21728)	2024-08-14 16:51:22 -07:00
test-types.ts	[js/webgpu] Manage model download with a specific unittest option (#22214)	2024-09-30 18:27:43 -07:00