← Latest products

Keep your PyTorch model in VRAM by hot swapping code

Pytorch script hot swap: Change code without unloading your LLM from VRAM.

Open source

127 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. GoTorch

    news.ycombinator.com

    A Go Implementation of PyTorch

    Hacker News9 pts

  2. CUDA/graphics in QEMU-KVM VMs without passing the Nvidia card to them

    github.com

    Paravirtual NVIDIA GPU for KVM guests — run unmodified CUDA, PyTorch and Vulkan inside a VM at host parity, on a GPU the host keeps using. No passthrough, no vGPU licence. Experimental.

    Hacker News5 pts

  3. Reimplementing PyTorch from scratch (MLP

    github.com

    CNN) to learn the internals

    Hacker News5 pts

  4. LeanRL

    github.com

    Fast PyTorch RL with Torch.compile and CUDA Graphs

    Hacker News53 pts

  5. TurboPilot

    github.com

    Copilot clone runs code completion LLM on your CPU

    Hacker News37 pts