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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: NCCL OOM at 1k concurrency using default memory for DP=16 decode with EPLB and 16 redundant experts
- [Bug]: Too many values to unpack in dispatch_cpu_unquantized_gemm [LiquidAi/LMF2]
- [Usage]: How to Add torch.cuda.nvtx Code in vLLM to Monitor Model GPU Usage
- [Bug]: gpt-oss-120b failed with data-parallel-size >1
- [Feature]: Disable ANSII colors in logs of OpenAI compatible server
- [RFC]: Generalized KV cache reuse
- [Bug]: VLLM V1 Engine crashes with KeyError when processing concurrent embedding requests
- [CPU] Fix uninitialized accumulators in attention kernels
- [compile] custom op unit test
- [Bug]: some models won't stream from s3: Qwen/Qwen3-VL-30B-A3B-Instruct-FP8
- Docs
- Python not yet supported