Read-only Rust CLI for inspecting KV-cache metrics from Prometheus snapshots
Executable mini-forms of LLM serving mechanisms - continuous batching, paged state, prefix caching, speculative decoding, the executor boundary, rank parallelism - as one dependency-free state machine with step-by-step traces
Trace-native, memory-safe inference engine for the Qwen3.8 family (Gated DeltaNet hybrid) — real-time observability for on-device inference
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