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]: Prefix caching is ineffective on Mamba-2/GDN hybrid (Qwen3_5MoeForConditionalGeneration)
- [Bug]: `MiniMAXGemmaRMSNorm` unconditionally calls FlashInfer CUDA kernels, breaking MiniMax-M3 on every non-CUDA platform
- feat: optimize MHC post + HC head + RMSNorm fusions for DeepSeek V4
- [Model] Add EVS video pruning support for Cosmos3-Edge
- Add feature to support deepseek v4 flash on sm75 turing (2080ti)
- [Perf][Hybrid] Skip redundant num_accepted_tokens H2D copy after preprocess_mamba
- [Bugfix] Restore default torch dtype on exception in set_default_torch_dtype
- [Bug]: nvidia/Kimi-K2.6-NVFP4 TP=4 segfaults during cuDNN vision profiling on GB200 ARM64 unless --language-model-only is set
- [Bug]: MinimaxM3ToolParser (Rust) fails on MiniMaxAI/MiniMax-M3-MXFP8 tool output; raw markup + ']<]minimax[>[' special token leaks into content
- [Bugfix][Rust] MiniMax-M3 tool parser: accept elided first-parameter opening tag
- Docs
- Python not yet supported