Kv Cache Python Packages

lmcache

Supercharge Your LLM with the Fastest KV Cache Layer

processfork

git for AI agents — snapshot, fork, and merge live LLM sessions in 8 ms. Drop-in for Claude Code, LangGraph, vLLM, SGLang.

quantcpp

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

llm-autotune

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.

fade-kv

Frequency-Adaptive Decay Encoding: Attention-aware tiered KV cache compression for LLM inference.

turboquant-vllm

TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs

turboquant-mlx-full

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

turboquant

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

avp

Python SDK for Agent Vector Protocol – transfer KV-cache between LLM agents instead of text

tqai

TurboQuant KV cache compression for local LLM inference

kvboost

Make LLM inference faster with chunk-level KV cache reuse

cappr

Completion After Prompt Probability. Make your LLM make a choice

memopt-engine

MEMOPT: Universal Memory Fabric for AI Infrastructure. Open-sourced by Sophisticates.

kakeyalattice

Discrete Kakeya cover for LLM KV cache: D4/E8 nested-lattice quantisation realising a Kakeya-style tube-cover over the direction sphere. 2.4x-2.8x compression at <1% perplexity loss on Qwen3, Llama-3, DeepSeek, GLM-4, Gemma. Drop-in transformers.DynamicCache. pip install kakeyalattice.

lmcache-cli

Supercharge Your LLM with the Fastest KV Cache Layer

fused-turboquant

Fused Triton kernels for TurboQuant KV cache compression — 2-4 bit quantization with RHT rotation. Drop-in HuggingFace & vLLM integration. Up to 4.9x KV cache compression for Llama, Qwen, Mistral, and more.

prismkv

3-D stacked-plane KV cache quantization + RAG framework. Defensive prior-art publication extending TurboQuant to conditional 3-D polar cells with adaptive bit allocation.

adaptq

High-performance CPU KV-cache quantization engine for LLM inference (~10× speedup, 4× memory reduction) with Python & PyTorch support.

turbokv

First open-source implementation of TurboQuant (arXiv 2504.19874) — 4-7x LLM KV cache compression. pip install turbokv

kvfleet

KV-cache-aware intelligent routing for self-hosted and hybrid LLM fleets. Route requests using model quality, latency, cost, policy, and live GPU state.

kvat

Automatic KV-Cache optimization for HuggingFace Transformers. Find the optimal cache strategy, attention backend, and dtype for your LLM inference workload.

langchain-turboquant

LangChain VectorStore with TurboQuant compression (ICLR 2026) - 6x memory reduction, training-free, no GPU required. The first LangChain integration for Google Research's TurboQuant algorithm.

nexusquant-kv

Training-free KV cache compression via E8 lattice quantization and attention-aware token eviction

phase-slip-sampler

An entropic perturbation sampler for LLMs using orthonormal vector rotation and logit anchoring.