Plant-level inference and control engine for AI infrastructure. Estimates plant state under partial observation, forecasts outcomes under specified actions, imposes interventions, and measures results.
From-scratch paged-attention inference engine: paged KV cache, continuous batching, preemption
Zero-code OpenTelemetry tracing for AI agents
Relay: minimal LLM inference server for heterogeneous devices
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page