ml-explore / ml-explore/mlx-examples
Implement RadixAttention in KV cache
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9k
- Forks
- 1.2k
- PR merge metrics
- No merged PRs in 30d
Description
Enhancement request:
Implement RadixAttention in the KV cache
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked RadixAttention paper and locating the repository's KV cache implementation and its tests. Determine how prefix sharing and cache updates should fit the existing design. Done means RadixAttention is implemented in the KV cache with coverage for its expected behavior, but the issue names no files or test entry points.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100