[AZ-180] Add Jetson Orin Nano support with INT8 TensorRT engine

- Dockerfile.jetson: JetPack 6.x L4T base image (aarch64), TensorRT and PyCUDA from apt
- requirements-jetson.txt: derived from requirements.txt, no pip tensorrt/pycuda
- docker-compose.jetson.yml: runtime: nvidia for NVIDIA Container Runtime
- tensorrt_engine.pyx: convert_from_source accepts optional calib_cache_path; INT8 used when cache present, FP16 fallback; get_engine_filename encodes precision suffix to avoid engine cache confusion
- inference.pyx: init_ai tries INT8 engine then FP16 on lookup; downloads calibration cache before conversion thread; passes cache path through to convert_from_source
- constants_inf: add INT8_CALIB_CACHE_FILE constant
- Unit tests for AC-3 (INT8 flag set when cache provided) and AC-4 (FP16 when no cache)

Made-with: Cursor

_docs/_autopilot_state.md

@@ -1,17 +1,22 @@
 # Autopilot State
 ## Current Step
 flow: existing-code
-step: 14
-name: Deploy
+step: 9
+name: Implement
 status: in_progress
-sub_step: 0
+sub_step: batch_01
 retry_count: 0
 
 ## Cycle Notes
-Previous full cycle (steps 1–14) completed. New cycle started for AZ-178.
+AZ-178 cycle (steps 8–14) completed 2026-04-02.
 step: 8 (New Task) — DONE (AZ-178 defined)
 step: 9 (Implement) — DONE (implementation_report_streaming_video.md, 67/67 tests pass)
 step: 10 (Run Tests) — DONE (67 passed, 0 failed)
 step: 11 (Update Docs) — DONE (docs updated during step 9 implementation)
 step: 12 (Security Audit) — DONE (Critical/High findings remediated 2026-04-01; 64/64 tests pass)
 step: 13 (Performance Test) — SKIPPED (500ms latency validated by real-video integration test)
+step: 14 (Deploy) — DONE (all artifacts + 5 scripts created)
+
+AZ-180 cycle started 2026-04-02.
+step: 8 (New Task) — DONE (AZ-180: Jetson Orin Nano support + INT8)
+step: 9 (Implement) — NOT STARTED