turboquant-pytorch cpprhtn · COMPLETED
From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.
github.com/cpprhtn/turboquant-pytorch · ★ 0 · Forks 0 · Size 23 KB
SUMMARY
Technologies 4
Scored 4
Observed 4
Practices 6
Evidence 5
Skips 0
COVERAGE
Analyzed 13 files · 4 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
9 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
TypeScript LANGUAGE Depth 54
1 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-03-25
Last commit 2026-03-30
Active months 1
Commits 4