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
- [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
- [XPU] Prefer MXFP8 MoE XPU backend; forward softcap/ALIBI
- [Bug]: Tiered KV offload promotes every waiting request (which fills primary DRAM pool)
- [Bug]: Cross-node Pipeline Parallelism (PP) fails with "invalid device ordinal" at PyNccl warmup on ROCm (AMD RDNA4 / R9700), reproducible on first inference even after context-corruption workaround
- [Bug]: SpeculativeConfig method="draft_model" cannot load mixed-precision compressed-tensors checkpoints (config_groups)
- Docs
- Python not yet supported