vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: crash:RecursionError: maximum recursion depth exceeded
- [Bug]: KeyError: 'layers.0.self_attn.qkv_proj.weight'
- [Performance]: vllm Eagle performance is worse than expected
- [Feature]: Support for Controlled Decoding
- [Performance]: bitsandbytes quantization slow
- [Feature]: google/gemma-2-2b supports 8K context length but vllm does not support it.
- [Frontend] Support suffix in completions API (fill-in-the-middle, FIM)
- [Bug]: Multiple inconsistencies wrt BOS injection and BOS duplication
- 【Frontend】Add sampler_priority and repetition_penalty_range
- [Model] Update MPT model with GLU and rope and add low precision layer norm
- Docs
- Python not yet supported