-
Notifications
You must be signed in to change notification settings - Fork 2
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
chore: Updating version matrix and trtllm template scripts #93
Conversation
@@ -38,6 +38,9 @@ matrix below: | |||
|
|||
| Triton CLI Version | TRT-LLM Version | Triton Container Tag | | |||
|:------------------:|:---------------:|:--------------------:| | |||
| 0.0.11 | v0.15.0 | 24.11 | |
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.
Do we want to copy over the convert_checkpoints.py
scripts for trtllm version 0.13.0 and 0.14.0 and release a new version of the CLI with the updated trtllm templates scripts being the main difference?
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.
Can the "Additional Dependencies for Custom Environments" section be updated as a part of this PR or left for a follow-up PR?
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.
The other PR will be removing the need for convert_checkpoint.py
scripts: #87, so this PR shouldn't be updating them.
Let's wrap up the LLM API changes first based on r24.09, then we can add smaller update PRs to just bump to 24.10 and 24.11.
Also "templates" means this folder: https://github.com/triton-inference-server/triton_cli/tree/main/src/triton_cli/templates/trt_llm, not the convert scripts.
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.
Reach out to me offline if you need any clarifications
This PR updates the documentation and TRTLLM
convert_checkpoints.py
scripts.