mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-27 22:45:57 +00:00
fac3e33da5
### Description This is a narrow implementation of Attention/MultiHeadAttention as it does not support: a. inputs 5-7 for MHA b. packed QKV/KV c. past/present d. attention mask But it works well for StableDiffusion and can be extended later. It reduces VRAM usage as it combines many ops into few I've updated demo here https://islamov.ai/stable-diffusion-webgpu/ it takes ~13sec for 1 image with 20 steps on RTX3090Ti and about 25s on M1 Pro VRAM usage is about 8gb if you don't use img2img Going to focus on SDXL now --------- Co-authored-by: Guenther Schmuelling <guschmue@microsoft.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| binding | ||
| jsep | ||
| proxy-worker | ||
| proxy-messages.ts | ||
| proxy-wrapper.ts | ||
| run-options.ts | ||
| session-handler-inference.ts | ||
| session-handler-training.ts | ||
| session-options.ts | ||
| wasm-common.ts | ||
| wasm-core-impl.ts | ||
| wasm-factory.ts | ||
| wasm-training-core-impl.ts | ||
| wasm-utils.ts | ||