RL-Kernel haoruilee · PARTIAL
Modern RL Post-training Infrastructure: Optimized for NVIDIA/AMD GPUs with a focus on vLLM and DeepSpeed integration, CUDA/ROCm/Triton kernels, and transparent hardware-aware scaling.
github.com/haoruilee/RL-Kernel · ★ 0 · Forks 0 · Size 28.2 MB
SUMMARY
Technologies 16
Scored 13
Observed 13
Practices 6
Evidence 18
Skips 3
COVERAGE
Analyzed 636 files · 1052 commits · 0 API calls
TECHNOLOGIES & DEPTH
Shell LANGUAGE Depth 70
6 files · PRODUCTION
C++ LANGUAGE Depth 70
1 files · PRODUCTION
JSON LANGUAGE Depth 70
23 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
86 files · PRODUCTION
YAML LANGUAGE Depth 70
10 files · PRODUCTION
Python LANGUAGE Depth 70
422 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
Black QUALITY Depth —
0 files · config only
NumPy LIBRARY Depth 74
4 files · PRODUCTION
Ruff QUALITY Depth —
0 files · config only
TypeScript LANGUAGE Depth 70
3 files · PRODUCTION
mypy QUALITY Depth —
0 files · config only
pandas LIBRARY Depth 58
1 files · PRODUCTION
pytest TESTING Depth 78
105 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-02-05
Last commit 2026-09-13
Active months 7
Commits 1052