vllm-project / vllm-project/vllm

[Feature]: lora support for deepseek v4.1 flash

Open
#57,166 1 comment 0 reactions 1 assignee Assigned to @linitra24 View on GitHub
deepseek DSv4.1 feature request
Dominant language
Python
Stars
92k
Forks
22.3k
PR merge metrics
PR metrics pending

Description

### 🚀 The feature, motivation and pitch

requesting to add support for https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash for fine tuning

### Alternatives

_No response_

### Additional context

_No response_

### Before submitting a new issue...

- [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the [documentation page](https://docs.vllm.ai/en/latest/), which can answer lots of frequently asked questions.

Contributor guide

Open the contributing guide

Research direction

No files, tests, or entry points are named. Start by reviewing how existing DeepSeek models and fine-tuning support are handled in vLLM, then determine the integration points required for DeepSeek-V4.1-Flash. Done means the model is supported for fine-tuning with documented validation.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.