NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy] PP sharding

Open
#4,323 1 comment 0 reactions 1 assignee View on GitHub

Nobody has claimed this yet.

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

Description

Currently, we don't support PP sharding. It is not clear whether we want to support PP sharding in the first place. Let's use this issue to discuss whether PP sharding is necessary and what it should entail.

We can also discuss considering PP + multi-node

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.