Open Issues Need Help
View All on GitHub documentation good first issue
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
documentation good first issue
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
enhancement good first issue tests
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
Add disk-backed (file) cache backend 6 days ago
enhancement good first issue roadmap:v0.2
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python