Factual package intelligence from PyPI

sgemm-bi 0.1.1.post2 package intelligence

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

Current version
0.1.1.post2
Python requirement
>=3.9
License
MIT OR Apache-2.0
Distribution type
Includes compiled wheel
Release files
2 (1 wheels, 1 source)
Download size
561.8 KiB
Release history
3 releases with files
Median release cadence
0 days

sgemm-bi dependencies

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.

Compatibility and release files

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.

Release activity and sources

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 .