merge: 合并远程 ft_wyt 分支，解决冲突

compute/api/main.py

@@ -221,6 +221,35 @@ def create_app() -> FastAPI:
             return fallback_gpu_resources()
 
         items: list[dict[str, Any]] = []
+        processes_by_uuid: dict[str, list[dict[str, Any]]] = {}
+        try:
+            process_result = subprocess.run(
+                [
+                    "nvidia-smi",
+                    "--query-compute-apps=gpu_uuid,pid,process_name,used_memory",
+                    "--format=csv,noheader,nounits",
+                ],
+                check=True,
+                capture_output=True,
+                text=True,
+                timeout=5,
+            )
+            for process_line in process_result.stdout.splitlines():
+                process_parts = [part.strip() for part in process_line.split(",")]
+                if len(process_parts) < 4:
+                    continue
+                process_uuid, pid, process_name, used_memory = process_parts[:4]
+                processes_by_uuid.setdefault(process_uuid, []).append(
+                    {
+                        "pid": int(_safe_float(pid)),
+                        "name": process_name,
+                        "memory_used_gb": round(_safe_float(used_memory) / 1024, 2),
+                    }
+                )
+        except Exception:
+            # Some driver/runtime combinations do not expose compute-apps;
+            # utilization and memory metrics remain useful without processes.
+            pass
         for line in result.stdout.splitlines():
             parts = [part.strip() for part in line.split(",")]
             if len(parts) < 9:
@@ -244,7 +273,7 @@ def create_app() -> FastAPI:
                     "temperature": int(_safe_float(temp)),
                     "power_w": round(_safe_float(power), 1),
                     "power_limit_w": round(_safe_float(power_limit), 1),
-                    "processes": [],
+                    "processes": processes_by_uuid.get(uuid, []),
                 }
             )
         return items
@@ -747,6 +776,23 @@ def create_app() -> FastAPI:
             infer_backend: str (default: "huggingface")
             infer_dtype: str (default: "auto")
         """
+        requested_gpus = payload.get("gpu_indices")
+        if requested_gpus is None:
+            requested_gpus = payload.get("gpus") or []
+        try:
+            requested_gpus = sorted({int(item) for item in requested_gpus})
+        except (TypeError, ValueError) as exc:
+            raise HTTPException(status_code=400, detail=f"invalid GPU selection: {exc}") from exc
+        if any(item < 0 for item in requested_gpus):
+            raise HTTPException(status_code=400, detail="GPU index must be non-negative")
+        if requested_gpus:
+            known_gpus = {int(item.get("gpu_index", item.get("id", -1))) for item in gpu_resources()}
+            missing = sorted(set(requested_gpus) - known_gpus)
+            if missing:
+                raise HTTPException(status_code=409, detail=f"requested GPU not found: {missing}")
+            conflict = sorted(set(requested_gpus).intersection(process_manager.locked_gpus()))
+            if conflict:
+                raise HTTPException(status_code=409, detail=f"GPU already used by another compute job: {conflict}")
         session = get_inference_session()
         result = session.load(
             model_name_or_path=payload.get("model_name_or_path", ""),
@@ -754,6 +800,7 @@ def create_app() -> FastAPI:
             template=payload.get("template", "qwen"),
             infer_backend=payload.get("infer_backend", "huggingface"),
             infer_dtype=payload.get("infer_dtype", "auto"),
+            gpu_indices=requested_gpus,
         )
         return result