[Feature]: AutoDeploy: PT-native hidden state management
Open
Nobody has claimed this yet.
AutoDeploy
feature request
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
Deprecate ADHiddenStateManager and instead directly interface with PT's hidden state manager.
This is pending on support for using cache handlers in AutoDeploy to integrate with the KVCacheManager and can be handled in the same fashion, see https://github.com/NVIDIA/TensorRT-LLM/issues/10013
Alternatives
No response
Additional context
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.
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.
Assessment
This issue has not been assessed yet.