Jiajia Qin 0409c639f7 [js/webgpu] Optimize MultiHeadAttention|Transpose (#22420) ... ### Description <!-- Describe your changes. --> With this optimization, 96 MultiHeadAttention|Transpose ops in phi3 disappear. Phi3 becomes 113 tokens from 107 tokens on my dGPUs. The optimization mainly skips the transpose op if one of the transposed dims is 1. Reshape is enough.		2024-10-14 15:43:14 -07:00
..
jsep	[js/webgpu] Optimize MultiHeadAttention|Transpose (#22420)	2024-10-14 15:43:14 -07:00
proxy-worker
proxy-messages.ts	[WebNN EP] Enable IO Bindings with MLTensor (#21301)	2024-09-27 17:24:21 -07:00
proxy-wrapper.ts
run-options.ts
session-handler-inference.ts	[WebNN EP] Enable IO Bindings with MLTensor (#21301)	2024-09-27 17:24:21 -07:00
session-options.ts
wasm-common.ts	[WebNN EP] Enable IO Bindings with MLTensor (#21301)	2024-09-27 17:24:21 -07:00
wasm-core-impl.ts	[WebNN EP] Enable IO Bindings with MLTensor (#21301)	2024-09-27 17:24:21 -07:00
wasm-factory.ts
wasm-types.ts	[WebNN EP] Enable IO Bindings with MLTensor (#21301)	2024-09-27 17:24:21 -07:00
wasm-utils-env.ts
wasm-utils-import.ts
wasm-utils-load-file.ts
wasm-utils.ts