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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: GLM5.2 RuntimeError: The expanded size of the tensor (10210) must match the existing size (16384) at non-singleton dimension 1. Target sizes: [12, 10210]. Tensor sizes: [12, 16384]
- [WIP] add helion nvfp4 backend for batch_size=1(gemv)
- [Bug]: Out of Resource / block size error Kimi K2.7 on SM120 Blackwell with kv_cache_dtype fp8
- Fix write-after-write hazard in xpu KV RoPE triton kernel
- [Bug] DeepSeekV4-Flash produces incorrect output with inline system messages after PR #46025 when `preserved in-place`
- [HelionLinearBackend][3/N] Add HelionFP8ScaledMMLinearKernel
- [Feature]: Support for the OpenAI input_file content part
- [RFC]: KVarN: a calibration-free, variance-normalized sub-8-bit KV-cache quantization backend
- Qwen3-VL-8B-FP8 on RTX 5080 (Blackwell SM120) - engine init OK but generate() hangs silently
- [RFC]: Add Helion linear backend for vLLM
- Docs
- Python not yet supported