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.
☆1,043Apr 23, 2026Updated 3 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 2 months ago
- ☆41Mar 31, 2026Updated 4 months ago
- LLM inference in C/C++☆2,226Updated this week
- Experimental llama.cpp fork for inference research and development☆725Updated this week
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,712Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆7,003Jul 20, 2026Updated 2 weeks ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,562May 10, 2026Updated 2 months ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆422Jul 25, 2026Updated last week
- ☆391Apr 16, 2026Updated 3 months ago
- 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…☆222Updated this week
- ☆259Apr 5, 2026Updated 3 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆829Updated this week
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆836Jul 14, 2026Updated 3 weeks 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…☆1,038Apr 23, 2026Updated 3 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- vLLM TurboQuant☆611Jun 25, 2026Updated last month
- llama.cpp fork with additional SOTA quants and improved performance☆2,990Updated this week
- A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support…☆1,549Updated this week
- [Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing☆215Apr 13, 2026Updated 3 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆326Jul 1, 2026Updated last month
- ☆201Apr 5, 2026Updated 3 months ago
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆200May 15, 2026Updated 2 months ago
- UniMesh: Unifying 3D Mesh Understanding and Generation☆57Jul 14, 2026Updated 3 weeks ago
- Bonsai Demo☆2,149Updated 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.
- TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration☆1,713Mar 27, 2026Updated 4 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,106Updated this week
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆323Updated this week
- PolarEngine: vLLM plugin for PolarQuant quantized LLM inference — 75% FP16 speed at 2.3x less VRAM☆34Apr 13, 2026Updated 3 months ago
- `Paper repo for “Coherence-Guided Dead-Head Identification in Frozen Transformers,” including manuscript sources, figures, frozen result …☆49Apr 8, 2026Updated 3 months ago
- [CVPR 2026] When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models☆68Apr 11, 2026Updated 3 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆1,795Updated this week
- A vector index built on TurboQuant, written in Rust with Python bindings☆14,599Updated this week
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 3 months ago
- Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.☆69,461Updated this week
- The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics☆73Mar 26, 2026Updated 4 months ago
- Implementation of <Streaming Autoregressive Video Generation via Diagonal Distillation> in ICLR 2026☆129Mar 18, 2026Updated 4 months ago
- PrismMl Bonsai vs Qwen3.5 Benchmark☆111Jul 14, 2026Updated 2 weeks ago
- Running a big model on a small laptop☆4,039Mar 19, 2026Updated 4 months ago
- Adaptive Test-time Learning and Autonomous Specialization☆2,069Updated this week