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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix: Nemotron 3 rescue whitespace-only final_content, not just None
- [Bug]: ValueError when CUDA_VISIBLE_DEVICES is a MIG device UUID
- [Bug]: Engine crashes on startup with 'DeepGEMM backend not available' for standard bf16 models on H100
- [Bug]: vLLM+UCCL-EP: DeepGemm CUDA Illegal Address at EP=64
- [Bug]: agrs Workspace Buffer Sizing Overflow at Large EP
- [Bug]: EP Deadlock with Hybrid GDN/Mamba Architecture (Qwen3.5)
- Allow video_files in custom_mm
- [Bug]: Stale Triton kernel cache on DGX Spark (sm_121) produces silently garbled outputs — wiping ~/.triton/cache restores correctness
- [Bugfix] Zero stale is_prefilling in padded CUDA graph rows for Mamba
- [Bug]: AttributeError when loading Mamba2ForCausalLM with BitsAndBytes quantization
- Docs
- Python not yet supported