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
- [Bug]: Token truncation leaves stale Request.block_hashes and can cause incorrect KV cache hits
- [Bugfix] Fix pipeline parallelism for Kimi-Linear
- [Bug]: Decode instance segfaults on NIXL `loadRemoteMD` after prefill pod restarts in P/D disaggregation
- [Perf] [Feat] [ROCm] Add densemha support to ROCm AITER Sparse MLA
- Add vllm:kv_offload_cpu_total_blocks capacity metric
- [MoE][Kernel] Add optional HPC BF16xFP32 router GEMM
- fix(sampler): fall back to native sampling when flashinfer is absent
- [RFC]: Multimodal Asynchronous Collaborative Architecture Sidecar
- [Bug]: v0.25.0 regression - Qwen3.5 FP8 on H200 crashes during CUDA graph capture with CUDA illegal memory access
- Responses API: reasoning.context has no effect on input; prior-turn reasoning is re-rendered and re-verbalized as `<think>`
- Docs
- Python not yet supported