TransformerEngine JF-D · COMPLETED
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
github.com/JF-D/TransformerEngine · ★ 0 · Forks 0 · Size 23.4 MB
SUMMARY
Technologies 16
Scored 16
Observed 16
Practices 6
Evidence 17
Skips 0
COVERAGE
Analyzed 1057 files · 2063 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
C++ LANGUAGE Depth 70
148 files · PRODUCTION
Shell LANGUAGE Depth 70
38 files · PRODUCTION
JSON LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
11 files · PRODUCTION
TOML LANGUAGE Depth 70
3 files · PRODUCTION
YAML LANGUAGE Depth 70
24 files · PRODUCTION
Python LANGUAGE Depth 70
440 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 85
41 files · PRODUCTION, TEST
Pydantic LIBRARY Depth 58
1 files · PRODUCTION
Redis CACHE Depth 69
2 files · CONFIGURATION, TEST
TypeScript LANGUAGE Depth 78
48 files · PRODUCTION, TEST
pandas LIBRARY Depth 74
8 files · PRODUCTION
pytest TESTING Depth 78
108 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2022-09-27
Last commit 2026-08-21
Active months 48
Commits 2063