Trending repositories: gpu

8 tracked repositories tagged with gpu, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

8 of 8 repositories

  • Vaibhavs10/insanely-fast-whisper

    AI summary: An optimized implementation of OpenAI's Whisper model that runs transcription incredibly fast.

    13,041ai-mlJupyter NotebookApache-2.0

  • QuipNetwork/quip-miner

    The quip network mining stack. This includes a coordinator and links all of the official quip network miners.

    AI summary: A specialized Python mining client for solving Ising models on the Quip Network.

    11,602infrastructurePythonAGPL-3.0

  • Andyyyy64/whichllm

    Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

    AI summary: CLI tool to auto-detect hardware and rank best-fitting local LLMs from HuggingFace.

    6,152developer-toolsPythonMIT

  • ChartGPU/ChartGPU

    Beautiful, open source, WebGPU-based charting library

    AI summary: High-performance WebGPU charting library designed for dense, real-time multi-series dashboards.

    3,175webTypeScriptMIT

  • thu-pacman/chitu

    High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

    AI summary: A high-performance LLM inference engine supporting diverse GPUs and complex deployments.

    3,155infrastructurePythonApache-2.0

  • Zaneham/Booth

    Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.

    AI summary: A lightweight, self-hosted photo booth application for events.

    1,728webCApache-2.0

  • Zaneham/Booth

    Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.

    AI summary: An open-source compiler targeting AMD GPUs, NVIDIA PTX, and native CPUs from CUDA and Triton source.

    1,721infrastructureCApache-2.0

  • livehl/aimirror

    🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来

    AI summary: A smart, parallel-download proxy that accelerates PyPI, Docker, and HuggingFace in restricted networks.

    211developer-toolsPythonMIT