llm-inference-runtime amxson · COMPLETED
An LLM inference runtime built from first principles to explore and implement autoregressive decoding, KV caching, batching, scheduling, streaming, and inference optimizations.
github.com/amxson/llm-inference-runtime · ★ 0 · Forks 0 · Size 47 KB
SUMMARY
Technologies 6
Scored 6
Observed 6
Practices 6
Evidence 7
Skips 0
COVERAGE
Analyzed 23 files · 8 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
2 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
18 files · PRODUCTION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
pytest TESTING Depth 53
7 files · TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · absentcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-09-27
Last commit 2026-10-13
Active months 2
Commits 8