1.1.4 Release
Added
- Added Patching Support for
torch.nn.Sequential
containers. - Added support for modeling source and line resistances for passive crossbars/tiles.
- Added C++ and CUDA bindings for modeling source and line resistances for passive crossbars/tiles*.
- Added a new MemTorch logo to
README.md
- Added the
set_cuda_malloc_heap_size
routine to patchedtorch.mn
modules. - Added unit tests for source and line resistance modeling.
- Relaxed requirements for programming passive crossbars/tiles.
*Note it is strongly suggested to set cuda_malloc_heap_size
using m.set_cuda_malloc_heap_size
manually when simulating source and line resistances using CUDA bindings.
Enhanced
- Modularized patching logic in
memtorch.bh.nonideality.NonIdeality
andmemtorch.mn.Module
. - Updated
ReadTheDocs
documentation. - Transitioned from
Gitter
toGitHub Discussions
for general discussion.