ML-Sharp-Snapdragon-GPU-Previews

Start.ps1

@@ -105,10 +105,10 @@ Write-Host "系统信息" -ForegroundColor Cyan
 Write-Host "==============================================================================================" -ForegroundColor Cyan
 Write-Host ""
 Write-Host "支持模式:" -ForegroundColor Yellow
-Write-Host "  [OK] NVIDIA GPU (CUDA)" -ForegroundColor Green
-Write-Host "  [OK] AMD GPU (ROCm)" -ForegroundColor Green
-Write-Host "  [OK] Intel GPU (CPU 回退)" -ForegroundColor Green
-Write-Host "  [OK] CPU 模式" -ForegroundColor Green
+Write-Host "NVIDIA GPU (CUDA)" -ForegroundColor Green
+Write-Host "AMD GPU (ROCm)" -ForegroundColor Green
+Write-Host "Intel GPU (CPU 回退)" -ForegroundColor Green
+Write-Host "CPU 模式" -ForegroundColor Green
 Write-Host ""
 Write-Host "==============================================================================================" -ForegroundColor Cyan
 Write-Host ""
@@ -118,7 +118,7 @@ Write-Host ""
 Write-Host "==============================================================================================" -ForegroundColor Cyan
 Write-Host ""
 
-& $pythonPath "app.py" --enable-auto-tune
+& $pythonPath "app.py" --enable-auto-tune --config config/config.yaml
 
 # 错误处理
 if ($LASTEXITCODE -ne 0) {

config.yaml

@@ -1,58 +1,33 @@
-# MLSharp-3D-Maker 配置文件
-# 支持的格式: YAML
-
-# 服务配置
-server:
-  host: "127.0.0.1"        # 服务主机地址
-  port: 8000               # 服务端口
-
-# 启动模式
-mode: "auto"               # 启动模式: auto, gpu, cpu, nvidia, amd
-
-# 浏览器配置
-browser:
-  auto_open: true          # 自动打开浏览器
-
-# GPU 优化配置
-gpu:
-  enable_amp: true         # 启用混合精度推理 (AMP)
-  enable_cudnn_benchmark: true  # 启用 cuDNN Benchmark
-  enable_tf32: true        # 启用 TensorFloat32
-
-# 日志配置
-logging:
-  level: "INFO"            # 日志级别: DEBUG, INFO, WARNING, ERROR
-  console: true            # 控制台输出
-  file: false              # 文件输出
-
-# 模型配置
-model:
-  checkpoint: "model_assets/sharp_2572gikvuh.pt"  # 模型权重路径
-  temp_dir: "temp_workspace"                     # 临时工作目录
-
-# 推理配置
-inference:
-  input_size: [1536, 1536]  # 输入图像尺寸 [宽度, 高度] (默认: 1536x1536)
-
-# 优化配置
-optimization:
-  gradient_checkpointing: false  # 启用梯度检查点（减少显存占用，但会略微降低推理速度）
-  checkpoint_segments: 3         # 梯度检查点分段数（暂未使用）
-
-# 缓存配置
-cache:
-  enabled: true                  # 启用推理缓存（默认：启用）
-  size: 100                      # 缓存最大条目数（默认：100）
-
-# 监控配置
-monitoring:
-  enabled: true            # 启用监控
-  enable_gpu: true         # 启用 GPU 监控
-  metrics_path: "/metrics" # Prometheus 指标端点路径
-
-# 性能配置
-performance:
-  max_workers: 4           # 最大工作线程数
-  max_concurrency: 10      # 最大并发数
-  timeout_keep_alive: 30   # 保持连接超时(秒)
-  max_requests: 1000       # 最大请求数
+browser:
+  auto_open: true
+cache:
+  enabled: true
+  size: 100
+gpu:
+  enable_amp: true
+  enable_cudnn_benchmark: true
+  enable_tf32: true
+inference:
+  input_size:
+  - 1536
+  - 1536
+mode: auto
+monitoring:
+  enable_gpu: true
+  enabled: true
+  metrics_path: /metrics
+performance_cache:
+  best_config:
+    amp: false
+    cudnn_benchmark: false
+    description: 仅启用 TensorFloat32
+    name: 仅 TF32
+    tf32: true
+  gpu:
+    compute_capability: 89
+    name: NVIDIA GeForce RTX 4060 Laptop GPU
+    vendor: NVIDIA
+  last_test: '2026-01-31T04:59:43.901644+00:00'
+server:
+  host: 127.0.0.1
+  port: 8000

gpu_utils.py

@@ -68,18 +68,55 @@ def check_rocm_available():
     except Exception:
         return False
 
+def check_adreno_available():
+    """检查 Adreno (Snapdragon) GPU 是否可用"""
+    try:
+        import torch
+        # Snapdragon GPU 通常通过 OpenCL/Vulkan，而不是 CUDA
+        # 检查是否为 Android 环境
+        if hasattr(torch, 'backends') and hasattr(torch.backends, 'opencl'):
+            if torch.backends.opencl.is_available():
+                return True
+        # 检查是否有 qnn 或 snpe 相关模块
+        try:
+            import importlib
+            if importlib.util.find_spec('qnn') or importlib.util.find_spec('snpe'):
+                return True
+        except:
+            pass
+        return False
+    except Exception:
+        return False
+
+
 def get_gpu_info():
     """获取 GPU 详细信息"""
     try:
         import torch
         if not torch.cuda.is_available():
+            # 检查是否为 Snapdragon GPU (通过 OpenCL)
+            if check_adreno_available():
+                return {
+                    'name': 'Snapdragon Adreno GPU',
+                    'count': 1,
+                    'cuda_version': None,
+                    'is_rocm': False,
+                    'is_adreno': True,
+                    'vendor': 'Qualcomm',
+                    'compute_capability': 0,
+                    'major': 0,
+                    'minor': 0,
+                    'memory_gb': 0,
+                    'multi_processor_count': 0,
+                }
             return None
 
         gpu_info = {
             'name': torch.cuda.get_device_name(0),
             'count': torch.cuda.device_count(),
             'cuda_version': torch.version.cuda,
             'is_rocm': check_rocm_available(),
+            'is_adreno': False,
         }
 
         props = torch.cuda.get_device_properties(0)
@@ -101,11 +138,16 @@ def get_gpu_vendor(gpu_name=None):
         gpu_info = get_gpu_info()
         if gpu_info:
             gpu_name = gpu_info.get('name', '')
+            # 直接从 gpu_info 检查 is_adreno 标记
+            if gpu_info.get('is_adreno'):
+                return 'Qualcomm'
         else:
             return 'Unknown'
 
     name_lower = gpu_name.lower()
-    if 'nvidia' in name_lower or 'geforce' in name_lower or 'quadro' in name_lower or 'tesla' in name_lower or 'rtx' in name_lower or 'gtx' in name_lower:
+    if 'snapdragon' in name_lower or 'adreno' in name_lower or 'qualcomm' in name_lower:
+        return 'Qualcomm'
+    elif 'nvidia' in name_lower or 'geforce' in name_lower or 'quadro' in name_lower or 'tesla' in name_lower or 'rtx' in name_lower or 'gtx' in name_lower:
         return 'NVIDIA'
     elif 'amd' in name_lower or 'radeon' in name_lower or 'rx' in name_lower:
         return 'AMD'

requirements.txt

@@ -2,10 +2,21 @@
 torch>=2.0.0
 torchvision>=0.15.0
 
+# ONNX Runtime for GPU Acceleration
+onnxruntime-gpu>=1.16.0; platform_system == "Windows"
+onnxruntime>=1.16.0; platform_system != "Windows"
+
 # FastAPI and Server
 fastapi>=0.128.0
 uvicorn[standard]>=0.40.0
 python-multipart>=0.0.21
+pydantic>=2.0.0
+
+# Caching
+redis>=5.0.0
+
+# Webhook and HTTP
+httpx>=0.25.0
 
 # 3D Gaussian Splatting
 sharp>=0.1.0

viewer.html

@@ -1404,7 +1404,7 @@ <h1>3DGS.ART</h1>
             formData.append('file', file);
 
             try {
-                const response = await fetch('/api/predict', {
+                const response = await fetch('/v1/predict', {
                     method: 'POST',
                     body: formData
                 });
@@ -1425,7 +1425,7 @@ <h1>3DGS.ART</h1>
             } catch (err) {
                 clearInterval(timer);
                 console.error(err);
-                alert("Preview Mode: Backend not connected.\nUse '?url=...' to load external models.");
+                alert("Error: " + err.message + "\n\nPreview Mode: Backend not connected.\nUse '?url=...' to load external models.");
                 loadingSys.stop();
             }
         }