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

Performance Optimization guide updates #2334

Closed
chauhang opened this issue May 10, 2023 · 2 comments
Closed

Performance Optimization guide updates #2334

chauhang opened this issue May 10, 2023 · 2 comments
Assignees
@sekyondaMeta
Labels
documentation Improvements or additions to documentation perf Performance issue

Comments

@chauhang
Copy link
Contributor

📚 The doc issue

Add a performance optimization guide consolidating all the best practices in one place with links to relevant references

Current Performance Tuning Guide
TorchServe Performance Tuning Sketch Animator case study
Better Transformers
Intel CPU Performance Optimizations for TorchServe
Nvidia MPS support for optimizing bin packing on GPUs for smaller models

Suggest a potential alternative/fix

No response
@chauhang chauhang changed the title Performance Optimization guide Performance Optimization guide updates May 10, 2023
@sekyondaMeta
Copy link
Contributor

This sounds like a good idea. I will work on a doc plan for this. I assume the plan is to add this to the Torchserve site.

@msaroufim msaroufim added documentation Improvements or additions to documentation perf Performance issue labels May 19, 2023
This was referenced Jun 6, 2023
Closed
Closed
Closed
Closed
This was referenced Jun 19, 2023
Closed
Merged
@chauhang
Copy link
Contributor Author

Performance guide has been updated

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@sekyondaMeta sekyondaMeta

Labels
documentation Improvements or additions to documentation perf Performance issue
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@msaroufim @chauhang @sekyondaMeta