NVIDIA / NVIDIA/TensorRT-LLM

[Bug]: Fix TPS/User glitches in BTK

Open
#11,936 1 comment 0 reactions 1 assignee View on GitHub

@marinayanov is already working on this.

Since Mar 5, 2026.

bug
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

System Info

spikes of TPS/User is seen in the IBP graphs, especially for VLLM as seen in the image below. This is due to cpu bottleneck in the sampler, and can be fixed by increasing the number of api workers. See this: https://nvidia.slack.com/archives/C09H79C4MB8/p1772128612444079?thread_ts=1772088513.942399&cid=C09H79C4MB8

This should be fixed in all our supported frameworks.

Image
Who can help?

No response

Information
  • The official example scripts
  • My own modified scripts
Tasks
  • An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
  • My own task or dataset (give details below)
Reproduction

na

Expected behavior

na

actual behavior

na

additional notes

na

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.