Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CUDA Graph性能优化 #2092

Open
GoHomeToMacDonal opened this issue Feb 23, 2025 · 1 comment
Open

CUDA Graph性能优化 #2092

GoHomeToMacDonal opened this issue Feb 23, 2025 · 1 comment
Labels
todolist

Comments

@GoHomeToMacDonal
Copy link

GoHomeToMacDonal commented Feb 23, 2025 •
edited
Loading

基于torch的CUDA graph capture优化AR model的解码速度，batch_size=1在RTX 3090上推理速度大概提升3.5倍，普通短句的 RT< 0.5s，体感会改善很多。在ubuntu上测试正常，目前还在测试windows。

Image

目前，初步完成了batch_size=1的的版本 CUDA Graph Test 。
@KamioRinn
Copy link
Contributor

v3暂不支持并行，可以先优化infer_panel_naive

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
todolist
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@KamioRinn @RVC-Boss @GoHomeToMacDonal