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

TRT LLM Integration with LORA #3305

Merged
merged 20 commits into from
Sep 17, 2024
Merged

TRT LLM Integration with LORA #3305

merged 20 commits into from
Sep 17, 2024

Conversation

agunapal
Copy link
Collaborator

@agunapal agunapal commented Sep 6, 2024

Description

This PR integrates TRT-LLM with TorchServe

  • Move handler from examples to torch_handler
  • Update llama example to llama 3.1
  • Update to latest trt-llm
  • Add example for using LoRA model with trt-llm
  • Added support for trt-llm with llm_launcher

Fixes #(issue)

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Feature/Issue validation/testing

Please describe the Unit or Integration tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

  • Test A
    Logs for Test A

  • Test B
    Logs for Test B

Checklist:

  • Did you have fun?
  • Have you added tests that prove your fix is effective or that this feature works?
  • Has code been commented, particularly in hard-to-understand areas?
  • Have you made corresponding changes to the documentation?

@agunapal agunapal marked this pull request as ready for review September 6, 2024 18:58
@agunapal agunapal requested a review from mreso September 6, 2024 18:58
Copy link
Collaborator

@mreso mreso left a comment

Choose a reason for hiding this comment

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

Good starting points, main concerns are that we're not leveraging async and git clone in llm_launcher

examples/large_models/trt_llm/lora/README.md Outdated Show resolved Hide resolved
examples/large_models/trt_llm/lora/README.md Outdated Show resolved Hide resolved
ts/llm_launcher.py Outdated Show resolved Hide resolved
ts/llm_launcher.py Outdated Show resolved Hide resolved
ts/utils/hf_utils.py Show resolved Hide resolved
ts/llm_launcher.py Show resolved Hide resolved
@agunapal agunapal requested a review from mreso September 14, 2024 00:48
Copy link
Collaborator

@mreso mreso left a comment

Choose a reason for hiding this comment

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

Does not look like the async part is working. Was this tested with at least 2 requests simultaneously and are we getting two interleaved streams?

examples/large_models/trt_llm/lora/README.md Outdated Show resolved Hide resolved
ts/torch_handler/trt_llm_handler.py Outdated Show resolved Hide resolved
Copy link
Collaborator

@mreso mreso left a comment

Choose a reason for hiding this comment

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

LGTM now

@mreso mreso added this pull request to the merge queue Sep 17, 2024
Merged via the queue into master with commit d5e10de Sep 17, 2024
14 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