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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf] #48137 costs ~10.6% spec-decode acceptance and #48660 shifts output distributions on DeepSeek-V4-Flash — isolated via #48660-only arm on a production 2-node deployment
- [Bugfix][Kernel] Keep DeepGEMM FP8 quant inside opaque op for TMA scales
- Fix MTP position-zero embeddings
- [Bugfix] Forward SwiGLU alpha/beta to the Marlin NVFP4 MoE quant config
- [ROCm][AITER] Add GDN long-prefill split-QKV fast path
- [Bug]: Responses code_interpreter returns HTTP 500 when tool arguments omit required "code" field in experimental ParsableContext
- [Metrics] Export EPLB rebalancing state and events
- [Bug]: /metrics returns 500 when PROMETHEUS_MULTIPROC_DIR resolves to a network-backed/mounted volume (TP>1)
- [ROCm] Add VLLM_ROCM_CLONE_MMAP_WEIGHTS to avoid slow H2D copies from mapped weights
- [Bug]: PCP (#46570) broken for non-compress models (GLM-5.2, compress_ratio=1) — multiple crash paths
- Docs
- Python not yet supported