 Jon Saad-FalconandClaude Opus 4.6
|
2aebcd7d77
|
feat: Phase 23 — Differentiated functionalities
Trace-driven learning pipeline:
- TrainingDataMiner: extract SFT/routing/agent pairs from traces
- LoRATrainer: fine-tune local models from trace-derived data
- AgentConfigEvolver: rewrite agent configs from trace analysis
- LearningOrchestrator: coordinate mine→train→evolve cycle, wired into SystemBuilder
Eval framework (15 real IPW benchmarks):
- Datasets: SuperGPQA, GPQA, MMLU-Pro, MATH-500, Natural Reasoning, HLE,
SimpleQA, WildChat, IPW, GAIA, FRAMES, SWE-bench, SWEfficiency,
TerminalBench, TerminalBench Native
- Scorers: MCQ extraction, LLM-judge, exact match, structural validation
- CLI: jarvis eval list|run|compare|report
Composable abstractions:
- Recipe system: TOML composition of all 5 pillars (3 built-in recipes)
- Agent templates: 15 pre-configured TOML manifests with system prompts
- Bundled skills: 20 ready-to-use TOML skill manifests
- Operator recipes: researcher (4h), correspondent (5min), sentinel (2h)
102 files changed, ~11,500 lines added. 3241 tests pass (44 skipped).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-03-02 05:34:46 +00:00 |
|
|
Jon Saad-FalconandClaude 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 |
|