or run

tessl search
Log in

Version

Workspace
tessl
Visibility
Public
Created
Last updated
Describes
pypipkg:pypi/cupy-cuda101@9.6.x
tile.json

tessl/pypi-cupy-cuda101

tessl install tessl/pypi-cupy-cuda101@9.6.0

CuPy: NumPy & SciPy for GPU (CUDA 10.1 version)

Agent Success

Agent success rate when using this tile

87%

Improvement

Agent success rate improvement when using this tile compared to baseline

1.19x

Baseline

Agent success rate without this tile

73%

rubric.jsonevals/scenario-8/

{
  "context": "This criteria evaluates how well the engineer uses CuPy's broadcasting operations (broadcast_arrays, broadcast_to) to handle arrays with different shapes. The focus is on using the appropriate broadcasting functions rather than manual array manipulation.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Uses broadcast_arrays",
      "description": "Uses cupy.broadcast_arrays() in the broadcast_arrays_to_common_shape() function to broadcast multiple input arrays to a common shape",
      "max_score": 35
    },
    {
      "name": "Uses broadcast_to",
      "description": "Uses cupy.broadcast_to() in the expand_to_shape() function to broadcast a single array to the specified target shape",
      "max_score": 35
    },
    {
      "name": "Correct return values",
      "description": "Functions return arrays with correct shapes as specified: broadcast_arrays_to_common_shape returns list/tuple of arrays with common shape, expand_to_shape returns single array with target shape",
      "max_score": 15
    },
    {
      "name": "Handles input correctly",
      "description": "Functions correctly accept and handle the specified input parameters (list of arrays for broadcast_arrays_to_common_shape, single array and target_shape for expand_to_shape)",
      "max_score": 15
    }
  ]
}