FlexGen davidsmooke · PARTIAL
Running large language models like ChatGPT/GPT-3/OPT-175B on a single GPU. Up to 100x faster than other offloading systems.
github.com/davidsmooke/FlexGen · ★ 1 · Forks 0 · Size 35.9 MB
SUMMARY
Technologies 15
Scored 13
Observed 13
Practices 6
Evidence 24
Skips 2
COVERAGE
Analyzed 3549 files · 9 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
14 files · PRODUCTION
Shell LANGUAGE Depth 70
93 files · PRODUCTION
C++ LANGUAGE Depth 70
68 files · PRODUCTION
C LANGUAGE Depth 70
4 files · PRODUCTION
JSON LANGUAGE Depth 70
63 files · PRODUCTION
TOML LANGUAGE Depth 70
2 files · PRODUCTION
Markdown LANGUAGE Depth 70
504 files · PRODUCTION
YAML LANGUAGE Depth 70
50 files · PRODUCTION
Python LANGUAGE Depth 70
2316 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
Bundler BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 81
10 files · PRODUCTION
Pydantic LIBRARY Depth —
0 files · config only
pytest TESTING Depth —
0 files · config only
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2023-02-15
Last commit 2023-02-20
Active months 1
Commits 9