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]: RuntimeError "cancelled" when using pipeline parallelism with Qwen3-14B
- [Bug]: Encoder disaggregation example endpoint timeout (Only when PD disaggregation enabled)
- [DNM] Split MM standard test
- [Bug]: DeepSeek-OCR - segmentation fault during encoder cache initialization on WSL2
- [CI Failure]: mi325_4: Distributed Tests (4 GPUs)
- Enable FlashInfer Hopper FP8 attention
- Document Ray Serve LLM incompatibility with vLLM v1 engine for PD disaggregation
- [V1][Spec Decode][Feature] support tree attention in flash-linear-attenton
- [Bug]: Error occurred when I run an simple command: "TORCH_USE_CUDA_DSA=1 LMCACHE_CHUNK_SIZE=8 vllm serve /home/nbw/model/Qwen2-0.5B/ --port 8000 --kv-transfer-config '{"kv_connector":"LMCacheConnectorV1", "kv_role":"kv_both"}'"
- [Bug]: weights_not_loaded check failed when loading bf16 DeepSeek-V3.2-Exp
- Docs
- Python not yet supported