gpu-telemetry

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CUDA and Metal devices through llama.cpp RPC, and rebuilds the pipeline when a worker drops out.

Self-hosted benchmark console for local LLM servers: TTFT, prefill/decode tok/s across 1K–64K contexts, concurrency sweeps, GPU telemetry and MTP/draft-acceptance stats with browser-side history and comparison.

GPU monitor for local LLM rigs -- btop-style TUI, per-process VRAM for Ollama/vLLM, thermal automation, Prometheus + Grafana

Enterprise Multi-Node Hybrid RAG, PyTorch Neural Vector Reranker & GPU Compute Console

An integrated flagship MLOps platform combining GPU telemetry monitoring, model serving registries, LangChain RAG, edge video inference, sandboxed code execution, and LLM benchmarking.

Deterministic, offline GPU telemetry validation with machine-readable PASS/FAIL decisions, synthetic fixtures, and Windows/Linux CI.