exllamav2 brianconlan2023 · COMPLETED
A fast inference library for running LLMs locally on modern consumer-class GPUs
github.com/brianconlan2023/exllamav2 · ★ 1 · Forks 0 · Size 21.7 MB
SUMMARY
Technologies 11
Scored 11
Observed 11
Practices 6
Evidence 12
Skips 0
COVERAGE
Analyzed 294 files · 1459 commits · 0 API calls
TECHNOLOGIES & DEPTH
C++ LANGUAGE Depth 70
42 files · PRODUCTION
Markdown LANGUAGE Depth 70
5 files · PRODUCTION
YAML LANGUAGE Depth 70
8 files · PRODUCTION
Python LANGUAGE Depth 70
117 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 74
7 files · PRODUCTION
Pydantic LIBRARY Depth 70
4 files · PRODUCTION
Redis CACHE Depth 76
3 files · CONFIGURATION, TOOLING
Requests LIBRARY Depth 74
4 files · PRODUCTION
TypeScript LANGUAGE Depth 70
4 files · PRODUCTION
pandas LIBRARY Depth 70
3 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2023-08-30
Last commit 2026-03-04
Active months 27
Commits 1459