mirror of https://github.com/llvm/torch-mlir
25738b8c19
Attention often broadcasts a mask across the batch dimension as masking is usually performed the same across attention heads. Added this materialization to the mask dimensions optionally. |
||
---|---|---|
.. | ||
jit_ir_common | ||
ltc | ||
onnx_c_importer | ||
pt1 | ||
CMakeLists.txt |