Aristide021 opened a new pull request, #18201: URL: https://github.com/apache/tvm/pull/18201
Intel GNA (Gaussian Neural Accelerator) hardware is present in Intel Core Ultra processors. This backend enables TVM users to target Intel NPU hardware via OpenVINO's GNA integration. Features: - Pattern-based graph partitioning for GNA-compatible operations - JSON serialization for OpenVINO runtime integration - Support for dense/linear, 1D convolution, and ReLU operations - Automatic shape and dtype extraction for optimization - Comprehensive test coverage Supported operations: - Dense/Linear layers (relax.matmul) - 1D Convolution (relax.nn.conv1d) - ReLU activation (relax.nn.relu) This provides community access to Intel NPU acceleration through TVM's compilation pipeline. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
