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.

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

[TRTLLM] some clean up on trtllm handler #1248

Merged
merged 3 commits into from
Nov 2, 2023

Conversation

lanking520
Copy link
Contributor

Description

Clean up on the handler

@lanking520 lanking520 requested review from zachgk, frankfliu and a team as code owners November 1, 2023 18:23
@lanking520 lanking520 force-pushed the trtllm branch 2 times, most recently from 10e18f5 to 95c23e2 Compare November 2, 2023 00:15
_rolling_batch_cls = get_rolling_batch_class_from_str(
self.rolling_batch_type, is_mpi, self.model_config)
self.rolling_batch = _rolling_batch_cls(model_id_or_path, self.device,
if "trt_llm_model_name" in properties:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

instead of converting properties to kwargs in the handler, it's better if we pass the properties to the toolkit and handler everything there. This conversion misses trt_* properties that users can set

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

addressed

@lanking520 lanking520 merged commit 44fe030 into deepjavalibrary:master Nov 2, 2023
5 of 8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants