GeeeekExplorer

    GeeeekExplorer/nano-vllm

    #527 this week

    Nano vLLM

    deep-learning
    llm
    nlp
    machine-learning
    inference
    pytorch
    transformer
    Python
    MIT
    15.8K stars
    2.7K forks
    15.8K GitHub watchers
    Updated Oct 12, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #3 among Deep Learning repositories tracked this week, and #3 over the last 30 days; #527 of 2,845 repositories GStars tracks this week (top 19%).

    The project lists 12 contributors on GitHub.

    Peaked at #30 in the weekly ranking the week of Nov 23, its best in the past year.

    Use Cases & Benefits

    • Implements a lightweight, fast inference engine for large language models in Python.
    • Delivers comparable or better inference speed than vLLM with a clean, minimal codebase.
    • Use for efficient offline inference of transformer-based NLP models on limited hardware.
    • Ideal for developers needing a readable and customizable LLM inference implementation.
    • Use for benchmarking and optimizing inference performance with advanced techniques like tensor parallelism and CUDA graph.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present

    Watch-outs

    • No GitHub releases; pin a commit or tag instead of a release.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    A lightweight vLLM implementation built from scratch.

    Excerpt from the GeeeekExplorer/nano-vllm README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    2.7K+356

    Open issues

    99+21

    Compared with peers in Deep Learning

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth

    GeeeekExplorer/nano-vllm compared with Deep Learning repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    p-e-w/heretic35.5K+1.3K41124 days ago
    koharu-rs/koharu6.4K+4836330 days ago
    pytorch/pytorch105.0K+4496423 days ago
    sgl-project/sglang37.7K+156754 days ago
    CorentinJ/Real-Time-Voice-Cloning60.2K+075—
    GeeeekExplorer/nano-vllm15.8K+075—
    Category median37.7K+44964—

    Discover Repositories

    Search across tracked repositories by name or description