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
- [Feature]: MultiModal benchmark_latency, benchmark_throughput, and benchmark_online
- [Bug]: CUDA device detection issue with KubeRay distributed inference for quantized models
- [Bug]: The accuracy of vllm-Qwen2-VL-7B-Instruct is low.
- [Misc]: What is the relationship between max-num-seqs, max-num-batched-tokens and max-model-len?
- [Misc]: Can vLLM go out of memory during the decode phase if too many tokens are generated?
- [Bug]: OOM when running llama3.1-8B-Instruct
- [torch.compile] A simple solution to recursively compile loaded model: using phi3-small as an example
- [Bug]: 启动之后 用了一段时间 显存越占越多
- [Bug]: AsyncLLMEngine hangs when using `asyncio.gather` with vllm version 0.5.5
- [Bug]: Qwen72B service(TP=4) gets stuck after running N requests. The GPU utilization of 3 GPUs is at 100%, while 1 GPU is at 0%. Simultaneously, the CPU utilization is at 100%, and many requests are in CLOSE_WAIT status.
- Docs
- Python not yet supported