@mytec: iter3.5.1 ready for testing

backend/app/api/routes/gpu.py

@@ -33,3 +33,9 @@ async def gpu_set_device(request: SetDeviceRequest):
         return {"status": "ok", **result}
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
+
+
+@router.get("/diagnostics")
+async def gpu_diagnostics():
+    """Full GPU diagnostic info for troubleshooting detection issues."""
+    return gpu_manager.get_diagnostics()

backend/app/services/gpu_backend.py

@@ -167,6 +167,66 @@ class GPUManager:
             for d in self._devices
         ]
 
+    def get_diagnostics(self) -> dict:
+        """Full diagnostic info for troubleshooting GPU detection."""
+        import sys
+        import platform
+
+        diag = {
+            "python_version": sys.version,
+            "platform": platform.platform(),
+            "numpy": {"version": np.__version__},
+            "cuda": {},
+            "opencl": {},
+            "detected_devices": len(self._devices),
+            "active_backend": self._active_backend.value,
+        }
+
+        # Check CuPy/CUDA
+        try:
+            import cupy as cp
+            diag["cuda"]["cupy_version"] = cp.__version__
+            diag["cuda"]["cuda_runtime_version"] = cp.cuda.runtime.runtimeGetVersion()
+            diag["cuda"]["device_count"] = cp.cuda.runtime.getDeviceCount()
+            for i in range(diag["cuda"]["device_count"]):
+                props = cp.cuda.runtime.getDeviceProperties(i)
+                name = props["name"]
+                if isinstance(name, bytes):
+                    name = name.decode()
+                diag["cuda"][f"device_{i}"] = {
+                    "name": str(name),
+                    "memory_mb": props["totalGlobalMem"] // (1024 * 1024),
+                    "compute_capability": f"{props['major']}.{props['minor']}",
+                }
+        except ImportError:
+            diag["cuda"]["error"] = "CuPy not installed"
+            diag["cuda"]["install_hint"] = "pip install cupy-cuda12x"
+        except Exception as e:
+            diag["cuda"]["error"] = str(e)
+
+        # Check PyOpenCL
+        try:
+            import pyopencl as cl
+            diag["opencl"]["pyopencl_version"] = cl.VERSION_TEXT
+            diag["opencl"]["platforms"] = []
+            for p in cl.get_platforms():
+                platform_info = {"name": p.name.strip(), "devices": []}
+                for d in p.get_devices():
+                    platform_info["devices"].append({
+                        "name": d.name.strip(),
+                        "type": cl.device_type.to_string(d.type),
+                        "memory_mb": d.global_mem_size // (1024 * 1024),
+                        "compute_units": d.max_compute_units,
+                    })
+                diag["opencl"]["platforms"].append(platform_info)
+        except ImportError:
+            diag["opencl"]["error"] = "PyOpenCL not installed"
+            diag["opencl"]["install_hint"] = "pip install pyopencl"
+        except Exception as e:
+            diag["opencl"]["error"] = str(e)
+
+        return diag
+
     def set_device(self, backend: str, index: int = 0) -> dict:
         """Switch active compute device."""
         target_backend = GPUBackend(backend)