execute_distributed_matmul
Executes verified distributed matrix multiplication C = A x B across decentralized GPU workers with dynamic Freivalds verification and L402 settlement. Accepts file paths (.npy, .npz, .safetensors) or inline 2D JSON arrays.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"matrix_a": "<matrix_a>",
"matrix_b": "<matrix_b>"
},
"name": "execute_distributed_matmul"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| dtype | No | Computation precision ('fp32', 'fp16', 'bf16'). | fp32 |
| matrix_a | Yes | File path (.npy/.npz/.safetensors) or inline 2D array for matrix A (M x K). | |
| matrix_b | Yes | File path (.npy/.npz/.safetensors) or inline 2D array for matrix B (K x N). | |
| tile_size | No | Optional tile block size override. | |
| output_path | No | Optional output file path (.npy, .npz, or .safetensors) to write C. | |
| tensor_key_a | No | Optional tensor key when loading matrix_a from .safetensors or .npz. | |
| tensor_key_b | No | Optional tensor key when loading matrix_b from .safetensors or .npz. | |
| partitioning_strategy | No | Matrix partitioning topology. | output_grid_2d |