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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: DSR1 fp8/nvfp4 MTP with spec num 3 load weight failure
- [Bug]: fails to inference prompt ends with '.' ':' for video inputs
- [Usage]: I am unable to run the GLM-4.5-Air-REAP-82B-A12B-nvfp4 model on an RTX 5090.
- [Usage]: Extremly low token input speed for DeepSeek-R1-Distill-Llama-70B
- [Bug]: DeepSeek-V3.1-Terminus-BF16 run error
- [Bug]: Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
- [Usage]: Turn off reasoning for Kimi-K2-Thinking?
- [Bug]: B200 prefill performance with deepep HT is ~50% of H200
- [Bug]: How to run DeepSeek-V3.2 on 2 H100 nodes?
- [Bug]: v1 scheduler assert num_new_tokens > 0
- Docs
- Python not yet supported