YOLO26M-pose - ExecuTorch with XNNPACK (Dynamic Shapes)
YOLO26M-pose exported to ExecuTorch.pte format with XNNPACK backend for accelerated CPU inference.
Model Details
Base Model: Ultralytics YOLO26M-Pose Estimation
Format: ExecuTorch (.pte)
Backend: XNNPACK (CPU-optimized)
Quantization: FP32
File Size: 92.3 MB
Dynamic Shape Support
This model supports dynamic input shapes within the following constraints:
Dimension
Min
Max
Constraint
Height
320
8192
Multiple of 32
Width
320
8192
Multiple of 32
Batch
1
1
Static
Supported resolutions: 320×320, 640×640, 1280×1280, 2560×1440, 7680×4320 (8K), and any size that's a multiple of 32.
Usage
python
1import torch
2from executorch.runtime import Runtime
34# Load the model5withopen("yolo26m-pose_dynamic_xnnpack.pte","rb")as f:6 pte_buffer = f.read()78runtime = Runtime.get()9program = runtime.load_program(pte_buffer)10method = program.load_method("forward")1112# Run inference with different input sizes13for h, w in[(640,640),(1280,1280),(2560,1440)]:14 input_tensor = torch.randn(1,3, h, w)15 output = method.execute([input_tensor])16print(f"Input shape: {(h, w)}, Output shape: {output[0].shape}")
Model Architecture
YOLO26 is an end-to-end NMS-free object detector optimized for edge devices:
End-to-end design (no NMS post-processing required)
Up to 43% faster CPU inference than previous YOLO versions
Optimized for mobile and edge deployment
Performance
Based on Ultralytics YOLO26 benchmarks:
Metric
Value
Parameters
20.8M
Input Size
640×640 (training)
Inference
Supports 320-8192 px (multiples of 32)
Tasks
This model performs pose estimation, detecting human keypoints.
Output includes bounding boxes and 17 COCO keypoints per person.
Troubleshooting
Low confidence / incorrect outputs with non-contiguous inputs
If your outputs look wrong (for object-detection models this can show up as all confidences capped around ~0.20 / 20% and no detections), ensure the input tensor passed to ExecuTorch is contiguous.
