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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature Request] Memory Poisoning Protection for vLLM Serving via OWASP Agent Memory Guard
- [Bug]: Linear host RSS growth + step-up in E2E latency under sustained `max_tokens=1` classification load (Gemma-3-1b, V1, prefix caching)
- [ROCm][Cleanup] Remove stale AITER FA hybrid KV-cache TODO
- [Bug]: [Bug] Severe GPU Memory Leak and OOM with Native KV Offloading in Multi-Node PP=2 TP=8 Setup (v0.22.0)
- [Bug]: when set kv_cache_dtype to fp8 or fp8_e4m3 causes the d node to crash
- [Bug]: vLLM hangs during speculative decoding with MoE draft model near max_model_len under Data Parallelism (DP)
- [Draft][XPU] Initial enablement deepep on XPU
- [Usage]: [Question] Inconsistent inference results (completely opposite outputs) across identical environments despite temperature=0
- [Bugfix][CI] Fix `ImportError: libcudart.so.12: cannot open shared object file: No such file or directory`
- [Bug]: Qwen3-VL EVS video pruning crashes with CPU/CUDA device mismatch in _create_final_video_embeddings
- Docs
- Python not yet supported