Learn distributed ML by playing a sci-fi browser game
Hands-on distributed ML simulator—gamified learning for tensor parallelism without spinning up clusters.

Browser-based GPU cluster for LLM inference with HTTP API and SSE broker coordination.
Developers with spare GPU capacity, teams needing distributed inference
Modal · RunPod · Replicate
Hands-on distributed ML simulator—gamified learning for tensor parallelism without spinning up clusters.
WebGPU NumPy alternative that beats TensorFlow.js on speed and simplicity.
NumPy API on WebGPU with zero shader writing beats TensorFlow.js bloat for compute.
REAPI-compatible distributed compute without Docker, etcd, or third-party Raft.
Cohort-based GPU sharing cuts DeepSeek V3 costs from $14k to $40/month.
Sequential-dispatch methodology corrects 20x overestimation in prior WebGPU benchmarks.