KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
☆1,053Apr 23, 2026Updated 6 months ago
Alternatives and similar repositories for rotorquant
Users that are interested in rotorquant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM inference in C/C++☆64May 7, 2026Updated 5 months ago
- ☆41Mar 31, 2026Updated 6 months ago
- LLM inference in C/C++☆2,436Updated this week
- Experimental llama.cpp fork for inference research and development☆891Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,953Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆7,019Jul 20, 2026Updated 3 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,199Aug 18, 2026Updated 2 months ago
- ☆397Apr 16, 2026Updated 6 months ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆482Oct 14, 2026Updated last week
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆233Oct 13, 2026Updated last week
- ☆308Apr 5, 2026Updated 6 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,173Updated this week
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆863Aug 4, 2026Updated 2 months ago
- From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% a…☆1,049Apr 23, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率，量化感知训练的精度☆1,688Updated this week
- vLLM TurboQuant☆618Jun 25, 2026Updated 4 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,337Updated this week
- HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE sp…☆26Jun 23, 2026Updated 4 months ago
- ☆200Apr 5, 2026Updated 6 months ago
- Bonsai Demo☆3,437Updated this week
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆344Aug 19, 2026Updated 2 months ago
- [Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing☆219Apr 13, 2026Updated 6 months ago
- UniMesh: Unifying 3D Mesh Understanding and Generation☆57Jul 14, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆204May 15, 2026Updated 5 months ago
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆425Oct 12, 2026Updated last week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,744Updated this week
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆14,763Updated this week
- TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration☆1,806Sep 3, 2026Updated last month
- TokenSpeed is a speed-of-light LLM inference engine.☆2,782Updated this week
- PolarEngine: vLLM plugin for PolarQuant quantized LLM inference — 75% FP16 speed at 2.3x less VRAM☆36Apr 13, 2026Updated 6 months ago
- `Paper repo for “Coherence-Guided Dead-Head Identification in Frozen Transformers,” including manuscript sources, figures, frozen result …☆51Apr 8, 2026Updated 6 months ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆32,553Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- LLM inference in C/C++☆979Updated this week
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.☆78,550Updated this week
- A vector index built on TurboQuant, written in Rust with Python bindings☆17,422Oct 7, 2026Updated 2 weeks ago
- [CVPR 2026] When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models☆69Updated this week
- TFT (Training from Traces) benchmark: 5 scenarios comparing TFT pipeline vs Direct Training on SGD restaurant traces☆13Sep 7, 2026Updated last month
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 6 months ago
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 5 months ago