Factual package intelligence from PyPI
Deterministic, batch-invariant CUDA GEMM for PyTorch: bit-identical training matmuls (forward / dW / dX) in f32, bf16, f16, with an opt-in tensor-core tier. Requires Linux x86_64 + NVIDIA Ampere or newer.
pip install sgemm-bi
PyPI declares 0 unique dependency rules for this release. Environment markers are shown when supplied by the project.
This release declares no required runtime dependencies in its PyPI metadata.
sgemm-bi publishes 1 wheel and 1 source archive for version 0.1.1.post2. Wheel platform tags: manylinux_2_34_x86_64.
No version-specific Python classifiers are declared.
PyPI lists 3 releases with files. The first dated release is ; 3 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .