| refactor: implement async edge proxy for distributed inference
- Decouple monolithic inference into pure Python Pre, Infer, and
Post core components.
- Introduce InferenceCoordinator for zero-copy single-process inference.
- Refactor lerobot_policy_node into an Asynchronous Edge Proxy to
support Edge-Cloud split without breaking action_dispatch.
- Remove redundant base nodes (base_model_node, passive_inference_node)
and legacy component wrappers.
- Add pure_inference_node and cloud_inference.launch.py.
- Support runtime mode switching via robot_config YAML.
Signed-off-by: XiaoqiangWu <wuxiaoqiang.rtos@huawei.com>
| 2 个月前 |
| inference_service: add Ascend OM backends
Move the existing ACT OMModel and ACT wrappers from the LeRobot patch
stack into inference_service so issue #48 can be resolved without
carrying those patches in the submodule.
Keep CPU, CUDA, and NPU loading unchanged. Select the OM adapters
only when the explicit ascend_om or ascend_om_3403 backend is requested.
Delete the migrated LeRobot patches from the active patch lists and
keep tests covering backend selection and patch filtering.
Signed-off-by: Shi Xin <shixin21@h-partners.com>
| 25 天前 |
| inference_service: add Ascend OM backends
Move the existing ACT OMModel and ACT wrappers from the LeRobot patch
stack into inference_service so issue #48 can be resolved without
carrying those patches in the submodule.
Keep CPU, CUDA, and NPU loading unchanged. Select the OM adapters
only when the explicit ascend_om or ascend_om_3403 backend is requested.
Delete the migrated LeRobot patches from the active patch lists and
keep tests covering backend selection and patch filtering.
Signed-off-by: Shi Xin <shixin21@h-partners.com>
| 25 天前 |
| refactor: implement async edge proxy for distributed inference
- Decouple monolithic inference into pure Python Pre, Infer, and
Post core components.
- Introduce InferenceCoordinator for zero-copy single-process inference.
- Refactor lerobot_policy_node into an Asynchronous Edge Proxy to
support Edge-Cloud split without breaking action_dispatch.
- Remove redundant base nodes (base_model_node, passive_inference_node)
and legacy component wrappers.
- Add pure_inference_node and cloud_inference.launch.py.
- Support runtime mode switching via robot_config YAML.
Signed-off-by: XiaoqiangWu <wuxiaoqiang.rtos@huawei.com>
| 2 个月前 |
| inference_service: support RKNN distributed runtime
Support RKNN artifacts in the distributed inference flow so the board runtime can
load .rknn models while keeping LeRobot checkpoint metadata for edge-side
preprocessing and postprocessing.
Align the live dispatcher defaults, board packaging, launch docs, and reliable
controller command QoS with the measured RKNN deployment path.
Defer optional backend imports so RKNN and CPU paths remain importable and
testable without Ascend runtime packages installed.
Signed-off-by: XiaoqiangWu <wuxiaoqiang.rtos@huawei.com>
| 24 天前 |
