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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [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
- [Feature][Model Runner V2] Support extract_hidden_states speculation
- [XPU] Prefer MXFP8 MoE XPU backend; forward softcap/ALIBI
- [Bug]: [MTP] ValueError when loading zai-org/GLM-OCR with MTP speculative decoding (model.layers.16.mtp_block uninitialized)
- [Feature][Frontend] Make strict tool calling an explicit override
- [Bug]: Tiered KV offload promotes every waiting request (which fills primary DRAM pool)
- [Linear] [Kernel] add block-wise scaled_mm
- [1/N] Unify multiple-path encoder cuda graph support
- Docs
- Python not yet supported