Yang Gu 53de2d8cb0 [js/webgpu] Enable GroupedConvVectorize path (#19791) ... Vectorize met 2 failed cases in a CI bot with NVIDIA GPU, but we couldn't repro with all the GPUs at hand, including NVIDIA GPUs. This PR introduces GPUAdapterInfo and enables this opt on non-NVIDIA GPUs to make the bots happy. No obivous perf gain can be seen if we enable vectorize on NVIDIA. However, it shows big perf improvement on Intel. On my Gen12 Intel GPU, mobilenetv2-12 perf was improved from 11.14ms to 7.1ms.		2024-03-12 22:25:07 -07:00
..
binding	[js/webgpu] Support capture and replay for jsep (#18989)	2024-01-30 18:28:03 -08:00
jsep	[js/webgpu] Enable GroupedConvVectorize path (#19791)	2024-03-12 22:25:07 -07:00
proxy-worker	[js/web] transfer input buffer back to caller thread (#19677)	2024-03-01 14:50:06 -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] enable external data loading for ort-web (#19087)	2024-01-12 19:24:24 -08:00
session-handler-training.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
session-options.ts	[js/webgpu] Support capture and replay for jsep (#18989)	2024-01-30 18:28:03 -08:00
wasm-common.ts	[js] changes to allow Float16Array if any polyfill is available (#19305)	2024-02-21 00:31:06 -08:00
wasm-core-impl.ts	[js/webgpu] expose a few properties in WebGPU API (#19857)	2024-03-12 19:50:51 -07:00
wasm-factory.ts	[js/web] show warning when numThreads is set but threads is not supported (#19179)	2024-01-17 15:04:22 -08:00
wasm-training-core-impl.ts	[js/web] revise backend registration (#18715)	2023-12-20 14:45:55 -08:00
wasm-utils-load-file.ts	[js/web] allow proxy to load model with 1GB <= size < 2GB (#19178)	2024-01-17 15:03:43 -08:00
wasm-utils.ts