Switch from Vega20 (gfx906) base to ROCm 7.2 for gfx1151; set local ollama :11435

TODO.md

@@ -0,0 +1,23 @@
+# TODO: marker-api Local Deployment
+
+## Priority 1: Verify local GPU compute works
+- [x] PyTorch ROCm sees gfx1151 on host
+- [x] Ollama runs locally on port 11435 with ROCm
+- [x] Start marker-api container with rocm/pytorch base
+- [ ] Verify `/health` shows `torch_device: cuda`
+- [ ] Run `convert_both.py` — ensure `non_llm` outputs are produced
+
+## Priority 2: Fix LLM correction pipeline
+- [ ] Remove Vega-specific `HSA_OVERRIDE_GFX_VERSION` from `app.py` ✅
+- [ ] Confirm `build_options()` fix (rm `use_llm` dup) resolves Click warnings ✅
+- [ ] Run `convert_both.py` and verify `non_llm` vs `llm` outputs differ
+- [ ] Confirm LLM requests reach local ollama container
+
+## Priority 3: Hardening
+- [ ] Add health check for LLM connectivity
+- [ ] Ensure `marker` user can write to `conversion_results` directory
+- [ ] Expose LLM metrics/status in /health endpoint
+
+## Known issues
+- GPUs are considered "iGPU" by ollama (system memory, not VRAM)
+- `LD_LIBRARY_PATH` in entrypoint may need /opt/rocm/lib from the rocm/pytorch image