GitHub · C++
l3tchupkt/adaptq
High-performance C++17 KV cache compression engine for LLM inference with Python bindings, SIMD acceleration, and multi-backend support.
- Stars
- 32
- Forks
- 49
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: attention, avx2, cpu-optimization, inference, kv-cache, llm, python, pytorch, quantization, simd
Latest data point: Nov 22, 2026 · 32 stars · 49 forks