feat: Update CoreML device support and server controls
- Replace 'mps' with 'coreml' as the identifier for Apple CoreML Execution Provider across the codebase. - Remove Apple chip generation checks and ensure CoreML is available on all macOS arm64 devices. - Adjust ONNX Runtime session creation to use default CoreML configurations without forcing 'MLProgram'. - Implement support for MoGe-2 to utilize CoreML with static input shape requirements. - Enhance server panel to display restart and stop controls consistently across running states, including 'BUSY'. - Update UI tests to verify new behavior for server controls and cached model display. - Bump blendjob dependency version to 0.1.16 in packaging tests and configurations.
This commit is contained in:
@@ -64,7 +64,7 @@ Depth Plane、Cutout Depth 与 Normal Map 使用 MoGe-2,Remove Background 与
|
||||
|
||||
`ModelManager` 按模型族管理下载目录与 ONNX Session,同一族只保留最近使用的模型和 Device,避免同类模型重复占用资源。
|
||||
|
||||
BEN2、DA3、MoGe-2 与 Upscale 共用 ONNX Runtime 推理入口。CUDA Session 使用可收缩的 memory arena;单次图片、完整帧集合或完整 Upscale tile 集合只在最后一次模型运行结束时收缩空闲 arena。Session 持有的模型权重与执行计划继续由 `ModelManager` 缓存,后续相同模型与 Device 直接复用。CPU、DirectML 与 CoreML 按各自 Provider 的普通运行方式执行。
|
||||
BEN2、DA3、MoGe-2 与 Upscale 共用 ONNX Runtime 推理入口。CUDA Session 使用可收缩的 memory arena;单次图片、完整帧集合或完整 Upscale tile 集合只在最后一次模型运行结束时收缩空闲 arena。Session 持有的模型权重与执行计划继续由 `ModelManager` 缓存,后续相同模型与 Device 直接复用。CPU、DirectML 与 CoreML 按各自 Provider 的普通运行方式执行。macOS arm64 默认使用 CPU;用户可选择 `coreml`,由 ONNX Runtime CoreML Execution Provider 在 Apple CPU、GPU 与 Neural Engine 之间调度,不使用 PyTorch MPS backend。MoGe-2 的动态 ONNX 图只把静态输入 shape 分区交给 CoreML,其余节点由 CPU Provider 执行;其他模型不使用该限制。
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
|
||||
Reference in New Issue
Block a user