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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: In SamplingParams, setting n to a large value (e.g., 512) never finishes
- [Usage]: How to fix the batch size whiling decoding?
- [Usage]: What do max_num_seqs and max_model_len do
- [ CI ] Awq Marlin Integration Tests
- [Bug]: Is vllm support function call mode?
- [Bug]: No available block found in 60 second in shm
- [Feature]: Support DeepSeek-V2 - MI300x
- [Performance]: Flashinfer backend's improvement is marginal compared to FlashAttention backend for long context Qwen2-72b-instruct-128k
- [Feature]: support reward model API
- [Installation]: ERROR: No matching distribution found for torch==2.3.1
- Docs
- Python not yet supported