Geodd Model Engine

Models trained to write better kernels.

Our hardware-specific LLMs power AI agents that find bottlenecks in live inference and write hardware kernels to address them.

How it works

Production traffic guides every improvement.

The loop starts with live inference. Our agents use what they observe to write better kernels, test their changes, and put verified improvements back into serving.

View Mosaic benchmarks
  1. Observe real workloads

    Execution graphs, context lengths, and changing batch sizes show where inference spends time.

  2. Write better kernels

    Our AI agents use hardware-specific LLMs to generate and refine code for those bottlenecks.

  3. Test against the workload

    Check correctness and measure performance under the conditions that exposed the problem.

  4. Deploy and measure

    Release verified improvements into Geodd’s inference service, then monitor their effect on production performance.

  5. Feed the next cycle

    Successful kernels and measured results inform the next experiments and further fine-tuning of our hardware-specific LLMs.

Our Kernel Development Models

The models powering
this process.

Mosaic, Druze, and Strata power the agents in this process. Each is fine-tuned for the hardware it optimizes.

01 / CUDA

Mosaic · NVIDIA

Kernel development for NVIDIA GPUs and CUDA.

View benchmarks
02 / ROCm

Druze · AMD

Kernel development for AMD GPUs and ROCm.

Coming soon

03 / TT-Metalium

Strata · Tenstorrent

Kernel development for Tenstorrent accelerators and TT-Metalium.

Coming soon

Run locally

Run optimized kernels on your own GPU.

Our autonomous AI agents use Mosaic to develop model-specific runtime kernels. Free Docker images package these kernels with vLLM, SGLang, or TensorRT-LLM so you can test their performance and use them in your own projects.

Browse free runtimes
Inference on Geodd

Use the improvements through one API.

Verified kernel improvements feed back into Geodd’s inference service. Run the models you need through our API while we continue improving how they execute.