-
Notifications
You must be signed in to change notification settings - Fork 1.5k
feat: Update logits bitmask kernel to v3 #3009
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
/bot run |
PR_Github #253 [ run ] triggered by Bot |
/bot run |
PR_Github #292 [ run ] triggered by Bot |
PR_Github #253 [ run ] completed with state |
PR_Github #292 [ run ] completed with state |
/bot run |
PR_Github #310 [ run ] triggered by Bot |
PR_Github #310 [ run ] completed with state |
/bot run |
PR_Github #347 [ run ] triggered by Bot |
PR_Github #347 [ run ] completed with state |
/bot run |
PR_Github #433 [ run ] triggered by Bot |
PR_Github #433 [ run ] completed with state |
/bot run |
PR_Github #442 [ run ] triggered by Bot |
PR_Github #442 [ run ] completed with state |
/bot run |
PR_Github #491 [ run ] triggered by Bot |
PR_Github #491 [ run ] completed with state |
/bot reuse-pipeline |
PR_Github #527 [ reuse-pipeline ] triggered by Bot |
PR_Github #527 [ reuse-pipeline ] completed with state |
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.
LGTM
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
/bot reuse-pipeline |
PR_Github #535 [ reuse-pipeline ] triggered by Bot |
PR_Github #535 [ reuse-pipeline ] completed with state |
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
The XGrammar team provides important insights on the kernel workload. In most cases, the bitmask tensor is almost-full (bit values are 1) and almost-empty (bit values are 0).
Compared the kernel version on main (v2), the PR introduces the kernel developed in mlc-ai/xgrammar#186 (v3):
See https://github.com/mlc-ai/xgrammar/tree/main/examples/benchmark#benchmark-apply-token-bitmask-inplace-kernels for more perf numbers. Please see mlc-ai/xgrammar#186 for more background.