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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix uninitialized NVFP4 global scale causing inf overflow
- [Bug]: CUDA illegal memory access on H200 MiniMax-M2.5
- [Feature]: Load Mistral format LoRA when `--load-format=mistral` and `--enable-lora`
- [Bug]: LoRA loading fails for modules with numeric indices (e.g., to_out.0 in Diffusion Transformers)`
- [Bug]: Qwen 3.5 27B AWQ 4bit capturing CUDA graph fails
- [Bug]: AsyncScheduler crashes with AssertionError during Realtime ASR streaming (num_output_placeholders underflow)
- [Misc] Use VLLMValidationError consistently in SamplingParams._verify_args
- [Bug Fix] Qwen3.5-nvfp4 MTP Speculative Decoding Weight Shape Mismatch
- [Bug]: streaming mode+finish_reason length, delta content not empty with finish_reason length
- [Feature] [ROCm]: Enable AITER `fused_allreduce_rmsnorm`
- Docs
- Python not yet supported