[Feature]: vllm atom plugin to support deepseek v4 flash 0731

Open
#2,136 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Active
Tech stack
python
Domain
ai-infra-agents

Research direction

Start by reproducing the difference between atom native and the vllm plugin for DeepSeek v4 flash 0731 on Ubuntu 24 with an MI355X GPU, using dspark as the native reference. Trace the vllm plugin entry point and compare its behavior with the native path. Done means the vllm plugin can run this model successfully in the reported environment.

Written by the indexing model from the issue text.

Description

Suggestion Description

atom native can run deepseek v4 flash 0731 with dspark.
However, when we run atom as vllm plugin, it is not able to run

Operating System

Ubuntu 24

GPU

Mi355x

ROCm Component

No response

Dominant language
Python
Stars
184
Forks
149
Avg merge
2d 7h
Merged PRs (30d)
189

Contributor guide

No contributing guide indexed for this repository

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.

More from ROCm/ATOM

All issues in ROCm/ATOM

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.