A vector index built on TurboQuant, written in Rust with Python bindings

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

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

llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).

Based on the implementation of Google's TurboQuant (ICLR 2026) — Quansloth brings elite KV cache compression to local LLM inference. Quansloth is a fully private, air-gapped AI server that runs massive context models natively on consumer hardware with ease

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

Fused TBQ4 Flash Attention + MTP + Shared Tensors for llama.cpp — 82+ tok/s with lossless 4.25 bpv KV cache at 200K context on RTX 4090

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

TurboQuant 3-bit KV-cache quantization for llama.cpp

TurboQuant-compatible vector search plus graph memory for constrained RAG.

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

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

llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

Native Windows vLLM 0.26.0: CPython 3.13, CUDA 12.8, SM 7.5/8.6/8.9/12.0 for RTX 20/30/40/50, OpenAI-compatible serving, Triton/FlashAttention, 10 KV-cache formats, Multi-TurboQuant, and experimental CPU/RAM/NVMe prompt-KV offload. No WSL or Docker.

llama.cpp fork optimized for NVIDIA DGX Spark / GB10 (Blackwell, SM 12.1) — TurboQuant weights + KV, NVFP4, DFlash MTP

Unified KV-cache compression for LLM inference: 12 Python-native methods, Debian-tested isolated add-ons, Godzilla KVarN/TriAttention, exact Godzilla/Gigatoken profiles, CUDA weight sharing, and multi-GPU planning.

Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.

HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE speculative decoding, and full Wave32 kernel optimizations.

TypeScript implementation of Google's TurboQuant algorithm for near-optimal vector quantization. Zero dependencies, works in Node.js and browsers.

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement