-
Notifications
You must be signed in to change notification settings - Fork 74
[CI][sglang] Add benchmark from sglang #5341
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.
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
Conversation
|
Test run with benchmarks: Test run with tests: |
|
I added sglang pin and usage of sglang kernel for comparison |
|
@etiotto @whitneywhtsang Ready to merge |
| # eventually occur. | ||
|
|
||
| # Offsets and masks. | ||
| # offsets_am = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M).to(tl.int64) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why do you prefer to keep the regular pointer code as comments?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For reference
This is one of the key workloads provided by sglang team, I locally optimized code with tensor descriptor as an example for them.