metadata
license: mit
language: en
tags:
- efficient-inference
- quantization
- speculative-decoding
- kv-cache
- llm-optimization
- tiny-models
Tiny-Inference-Optimizer-Suite
Cost-aware inference optimizer that auto-selects best quantization + speculative decoding + KV-cache compression strategy.
Author:Samudhan (@samudhan2003)
This is my artifact combining 3 research threads into