onnxruntime
d9bf8561 - Adapt memory optimizer to fit PHI2 (#19757)

Commit
1 year ago
Adapt memory optimizer to fit PHI2 (#19757) ### Adapt memory optimizer to fit PHI2 Few improvements and bug fixes: 1. Fix bug related to transformer layer detection. 2. Use default reversed typo order to create recompute node, to avoid the leaf nodes are handled too late, then having lowest priority for execution. 3. Add early stop when activation's element count is constant and total element count < 1M. This can avoid overhead to search subgraphs. Using export ORTMODULE_MEMORY_OPT_LEVEL=1 to enable layerwise recompute, on given recipe, memory consumption dropped from ~22GB to ~13GB .
Author
Parents
Loading