New: the yasp Model Catalog is live →

Throughput, latency and speedup for every model and GPU, measured the same way.

Explore the Model Catalog
  • Impact Studies
  • Plans
  • Documentation
    Documentation
    Book a Demo
    Book a Demo
Explore yasp
  • Product

    Agentic compilation for any GPU

  • Model Catalog

    Benchmarked inference across models & GPUs

Ready to compile?
Request Access
Request Access
Documentation
Documentation
Speak with an Engineer
Speak with an Engineer
By Industry
  • Autonomous Driving

    For teams shipping AI to autonomous fleets

  • Robotics

    For robotics teams shipping AI to production

  • Edge AI

    For teams shipping AI to power-constrained devices

  • Cloud Training & Inference

    For teams where inference cost is the margin

  • Model Labs & AI Platforms

    For teams making target silicon competitive

  • Consumer-Scale Inference

    For teams where inference cost is the margin

  • GPU Cloud & Managed AI

    For teams making target silicon competitive

By Personas
    Ready to compile?
    Request Access
    Request Access
    Documentation
    Documentation
    Speak with an Engineer
    Speak with an Engineer
  • Blog

    Discover our latest news, articles, and collaborations

    Engineering

    Fine-Tuning Qwen 27B to Write AWS Trainium (NKI) Kernels

    Engineering

    More tokens per dollar on AWS Trainium2: optimizing Qwen3.5-35B-A3B in days

    Engineering

    Reward Hacking in GPU Kernel Optimization: Why Gaia Would Reject a 4709x Speedup

    Benchmarks

    16x Faster HIP Kernels on AMD MI300X: Why the Agent Harness Matters

    Ready to compile?
    Request Access
    Request Access
  • About yasp

    Meet the people who are building gaia and kronos. Find out where we came from, what drives us, and how to join

    • About yasp

      Building and scaling Platformless AI Infrastructure

    • Careers

      Discover open roles.

    Ready to compile?
    Request Access
    Request Access

    Hardware belongs to builders. It always did.

    Start with docs and benchmarks, or talk to the team about your deployment environment.

    Request Access
    Request Access
    Speak with an Engineer
    Speak with an Engineer

    Product

    ProductModel catalogDocuments

    Solutions by industry

    Edge-AIRoboticsAutonomous DrivingModel Labs & AI PlatformConsumer-Scale InferenceGPU-Cloud & Managed AI

    Solutions by use case

    Company

    AboutCareersImpact StudiesPlans

    Resources

    Blog

    © 2026 yasp

    Privacy policy

    Imprint

    Cookie Declaration