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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Multimodal] Register `cu_seqlens` replay padding for GLM-4.1V/Kimi-K2.5 encoder CUDA graphs
- [Perf][Kernel][Attention] Binary-search mm_prefix spans in Triton unified attention
- [Model] Nemotron-3.5-Transcribe: support ReplaySSM
- [XPU] Qwen3.5 specialized decode: mono decode kernels (`--monokernel`)
- [docker] Install AWS EFA in the main image; build DeepEP-EFA separately
- [Bugfix] Respect actual video fps and frame indices in MiMo-v2.6 timestamp generation
- [Model][Perf] Gemma 4: torch.compile for the native vision tower
- [Perf][Core] Bound FIFO eviction cost for duplicate prefixes
- [Bugfix][Structured Output] Honor request stop tokens in Guidance
- [ROCm][Perf][Qwen4Exp] Opt-in exact AITER IPC and INT4 QuickReduce collectives for the --enable-hc-sp layers
- Docs
- Python not yet supported