Jon Saad-Falcon and Claude Opus 4.6
7829e29392
refactor: consolidate 5 OpenAI-compat engine wrappers into single data-driven file
...
Replace vllm.py, sglang.py, llamacpp.py, mlx.py, lmstudio.py with
openai_compat_engines.py using dynamic class creation and registration.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-02 23:11:00 +00:00
Jon Saad-Falcon and Claude Opus 4.6
24972e3e52
Add Phase 12+13: energy measurement, install polish, PWA, cross-hardware
...
Phase 12 — Energy Measurement Upgrade:
- EnergyMonitor ABC with multi-vendor support (NVIDIA hw counters,
AMD amdsmi, Apple zeus-ml, CPU RAPL sysfs)
- EnergyBatch batch-level energy-per-token accounting
- SteadyStateDetector CV-based thermal equilibrium detection
- EnergyBenchmark with warmup phase
- InstrumentedEngine prefers EnergyMonitor over legacy GpuMonitor
- Telemetry store/aggregator extended with energy fields
Phase 13 — Install, Hosting, Cross-Hardware:
- jarvis doctor diagnostic command (8 checks, --json output)
- jarvis init post-setup guidance with engine-specific next steps
- README Quick Start section
- MLX engine backend (Apple Silicon → mlx recommendation)
- AMD VRAM/multi-GPU detection via rocm-smi
- PyTorch MPS device selection in orchestrator trainers
- PWA support (vite-plugin-pwa, service worker, manifest, icons)
- Server static file serving fix for PWA files
- Dockerfile.gpu.rocm + docker-compose.gpu.rocm.yml for ROCm
- Eval framework display module and efficiency metrics
2244 tests pass, 37 skipped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-26 20:09:07 +00:00
