Jiajia Qin fd6bab4250 [js/webgpu] Provide a vectorized algorithm for GroupedConv (#18884) ... ### Description This PR provides a vectorized algorithm for NHWC GroupedConv to improve performance. The aggregate time of GroupedConv in mobilenetv2-12 becomes ~1ms from ~4ms on Intel Alder Lake machine. About 20% improvement for the whole model.		2024-01-10 16:12:43 -08:00
..
binding	[js/web] wait for threadpool initialization (#18952)	2024-01-04 08:06:55 -08:00
jsep	[js/webgpu] Provide a vectorized algorithm for GroupedConv (#18884)	2024-01-10 16:12:43 -08:00
proxy-worker	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
proxy-messages.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
proxy-wrapper.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
run-options.ts
session-handler-inference.ts	[js/webgpu] Introduce trace support (#18928)	2024-01-03 10:13:17 -08:00
session-handler-training.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
session-options.ts	[WebNN EP] Support numThreads option for WebNN CPU device (#18054)	2023-11-12 16:45:10 -08:00
wasm-common.ts	[js/webgpu] support IO binding (#17480)	2023-09-29 11:24:42 -07:00
wasm-core-impl.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
wasm-factory.ts	[js/web] wait for threadpool initialization (#18952)	2024-01-04 08:06:55 -08:00
wasm-training-core-impl.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
wasm-utils.ts