Submit

Forge - GPU Kernel Optimization

@RightNow-AI

Visit Server
a month ago
Turn slow PyTorch into fast CUDA/Triton kernels. 32 parallel swarm agents optimize your code on real datacenter GPUs (B200, H200, H100, A100) with up to 14x speedup over torch.compile.
OverviewToolsComments

Comments

Try in Playground

Server Config

{
  "mcpServers": {
    "forge": {
      "command": "npx",
      "args": [
        "-y",
        "@rightnow/forge-mcp-server"
      ]
    }
  }
}
© 2025 MCP.so. All rights reserved.

Build with ShipAny.