NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: prefill context parallel or chunked pipeline parallel for long context inference

Open
#13,036 1 comment 0 reactions 1 assignee View on GitHub

@laikhtewari is already working on this.

Since Apr 14, 2026.

feature request Scale-out
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

For long context, to meeting TTFT prefill, prefill context parallel and chunked pipeline parallel are two ways to parallel handle one prefill request, to lower TTFT.

For DSA (deepseek V3.2 or GLM5), neither of above two features is supported

do you have plan ?

Alternatives

No response

Additional context

No response

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.