A lightweight vLLM implementation built from scratch.

The original implementation is incompatible with older GPU architectures such as V100 or T4. This repository provides compatibility by leveraging the torch_native attention backend.

• 🚀 Fast offline inference - Comparable inference speeds to vLLM
• 📖 Readable codebase - Clean implementation in ~ 1,200 lines of Python code
• ⚡ Optimization Suite - Prefix caching, Tensor Parallelism, Torch compilation, CUDA graph, etc.

pip install git+https://github.com/GeeeekExplorer/nano-vllm.git

If you prefer to download the model weights manually, use the following command:

huggingface-cli download --resume-download Qwen/Qwen3-0.6B \
  --local-dir ~/huggingface/Qwen3-0.6B/ \
  --local-dir-use-symlinks False

See example.py for usage. The API mirrors vLLM's interface with minor differences in the LLM.generate method:

from nanovllm import LLM, SamplingParams
llm = LLM("/YOUR/MODEL/PATH", enforce_eager=True, tensor_parallel_size=1)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256)
prompts = ["Hello, Nano-vLLM."]
outputs = llm.generate(prompts, sampling_params)
outputs[0]["text"]

See bench.py for benchmark.

Test Configuration:

• Hardware: RTX 4070 Laptop (8GB)
• Model: Qwen3-0.6B
• Total Requests: 256 sequences
• Input Length: Randomly sampled between 100–1024 tokens
• Output Length: Randomly sampled between 100–1024 tokens

Performance Results: