Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/onnx-runtime
ONNX Runtime — cross-platform ML inference optimizer. Convert PyTorch, TensorFlow, scikit-learn models to ONNX. GPU, CPU, and mobile acceleration. Quantization, graph optimization, and custom ops.
Passed 21 of 22 test cases with the skill, and 21 of 22 without it.
1 fixed20 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
My ONNX model file is too large for deployment. Can you write a Python script using ONNX Runtime's quantization module to apply dynamic 8-bit integer quantization to model.onnx and save it as model_quantized.onnx?
| Checked | Without skill | With skill |
|---|---|---|
| The script specifies weight_type=QuantType.QInt8 in the quantize_dynamic call. | Missed | Passed |
The instructions your model reads when the skill loads.
ONNX Runtime is a cross-platform ML inference engine that runs models in the ONNX format. Supports CPU, GPU (CUDA, DirectML), and mobile inference with graph optimizations, quantization, and custom operators.
uv pip install onnxruntime # CPU
uv pip install onnxruntime-gpu # CUDA
# Convert first: from transformers, PyTorch, etc.
import onnxruntime as ort
import numpy as np
session = ort.InferenceSession("model.onnx")
input_name = session.get_inputs()[0].name
output_name = session.get_outputs()[0].name
result = session.run([output_name], {input_name: np.random.randn(1, 3, 224, 224).astype(np.float32)})
print(result[0].shape)
# GPU inference
session = ort.InferenceSession("model.onnx", providers=["CUDAExecutionProvider"])
# Enable optimizations
options = ort.SessionOptions()
options.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL
session = ort.InferenceSession("model.onnx", sess_options=options)
test cases passed, vs 21 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.