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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Build] DeepGEMM wheel integration: planned cleanups
- [Bug]: deepseek v4 failed to work on R6000 GPU
- [Bug]: Gemma 4 KVCache CPU offloading broken
- KVConnector V1 external hit lookup is consumed as a reservation, but has no plan/abort lifecycle
- [Bug]: Scheduler deadlocks after VLLMValidationError when prompt exceeds max_model_len by 1 token
- [Bug]: DeepSeek-V4-Pro TP=16 fails fp8 block-shape check on shared_experts.down_proj — contradicts the official recipe
- [Bug]: vLLM serve with tensor-parallel-size=8 on Kubernetes + vGPU fails: NCCL TCPStore broken pipe, EngineCore initialization failed
- [Installation]: RuntimeError: FlashInfer requires GPUs with sm75 or higher when running vllm server
- rocm_attn: fix paged attention for custom KV cache layouts
- [ROCm] Fix #36180: OOB Q-load in `paged_attention_ll4mi_QKV_mfma4_kernel`
- Docs
- Python not yet supported