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

[Doubt] Inflight batching support in T5 #2417

Open
vguruju opened this issue Oct 3, 2024 · 1 comment
Open

[Doubt] Inflight batching support in T5 #2417

vguruju opened this issue Oct 3, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@vguruju
Copy link

vguruju commented Oct 3, 2024

Description

Flan-T5 was recently given support with C++ triton backend (ref), does it mean features like rolling_batch are available for T5 now?
As per this line, there is no support for Inflight Batching in TRTLLM for T5. Does it still hold true?

References

  • list reference and related literature
  • list known implementations
@vguruju vguruju added the enhancement New feature or request label Oct 3, 2024
@sindhuvahinis
Copy link
Contributor

That is just a comment not removed. T5 should work with c++ backend with inflight batching. Please give it a try.

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

No branches or pull requests
2 participants
@sindhuvahinis @vguruju