lm-sys / lm-sys/FastChat

[Feat] can vllm_worker support `use_dynamic_ntk`?

Open
#2,668 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

model_worker support use_dynamic_ntk for max_length=16k, can vllm backend support it?

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.

Research direction

Start by locating the model_worker entry point and the vllm backend path, then trace how max_length is handled for model options. Compare the existing use_dynamic_ntk support in model_worker with the vllm path; done means the vllm backend supports the option for 16k context lengths and has verification for that behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.