Lightning-AI / Lightning-AI/lightning-thunder
Achieve performance parity with AutoDeploy's pipeline
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 1.5k
- Forks
- 121
- PR merge metrics
- No merged PRs in 30d
Description
🚀 Feature
Achieve performance parity with AutoDeploy's pipeline by getting cache insertion working. This will show Thunder is a flexible replacement for their compilation process.
Motivation
Pitch
Alternatives
Additional context
Sub-Tasks
- Support the trtllm autodeploy flashinfer KV-Cached attention in Thunder
- subtask 2
- subtask 3
Contributor guide
No contributing guide indexed for this repository
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
No files, tests, or entry points are named. Start by reading linked issue #2472 and mapping its trtllm AutoDeploy and flashinfer KV-cached attention requirements; done means cache insertion works and Thunder reaches performance parity with AutoDeploy's pipeline, but the remaining subtasks need definition.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- compilers, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100