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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Engine hangs indefinitely during model weight loading for nvidia/Qwen3.5-397B-A17B-NVFP4 on Blackwell GPUs (RTX PRO 6000) with TP=4
- [Feature]: Add nemotron_json as built-in tool parser (NVIDIA Nemotron-Nano-9B-v2 plugin breaks against v0.20.x module reorg)
- [RFC]: Standardize KV-cache Layouts
- [Model] llama: add FP8 scale name remapping to LlamaForCausalLM and LlamaModel
- fix: replace assert with early return in get_pkg_version for non-Linux platforms
- [Bug]: `prompt_logprobs` depends on request order when prefix caching is enabled
- [Bug]:Qwen3.5 with reasoning-parser returns non-standard tool call format when enable_thinking=true
- [Frontend] Improve interactive input line editing
- Fix Mamba copy metadata high-bit pointers
- [Core] [Quantization] Pass `out_dtype` to linear methods
- Docs
- Python not yet supported