onnxruntime/js/web/lib/wasm/jsep
Satya Kumar Jandhyala 736cbb3925
[JS/WebGU] Support fp16 in Attention by performing the computation in fp32. (#20486)
### Description
Perform computation in fp32 and convert finally to fp16.



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-04-27 08:30:26 -07:00
..
webgpu [JS/WebGU] Support fp16 in Attention by performing the computation in fp32. (#20486) 2024-04-27 08:30:26 -07:00
backend-webgpu.ts [JS/WebGPU] Multihead attention improvements (#20286) 2024-04-23 12:39:49 -07:00
init.ts [JS/WebGPU] Multihead attention improvements (#20286) 2024-04-23 12:39:49 -07:00
log.ts
tensor-view.ts [js/web] revise TensorView (#17473) 2023-09-14 21:14:44 -07:00
util.ts [js/webgpu] allows a ProgramInfo's RunData to use zero sized output (#19614) 2024-02-23 12:52:47 -08:00