abetlen / abetlen/llama-cpp-python
Add batched inference
Open
enhancement
high-priority
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 1.4k
- PR merge metrics
- PR metrics pending
Description
- [x] Use `llama_decode` instead of deprecated `llama_eval` in `Llama` class
- [ ] Implement batched inference support for `generate` and `create_completion` methods in `Llama` class
- [ ] Add support for streaming / infinite completion
Contributor guide
Assessment
This issue has not been assessed yet.