From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.
☆1,048Apr 23, 2026Updated 6 months ago
Alternatives and similar repositories for turboquant-pytorch
Users that are interested in turboquant-pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration☆1,818Sep 3, 2026Updated 2 months ago
- Experimental Rust vector-compression sidecars implementing TurboQuant (ICLR 2026), PolarQuant and QJL research primitives, with exact rer…☆28Oct 25, 2026Updated 3 weeks ago
- ☆7,027Jul 20, 2026Updated 3 months ago
- ☆200Apr 5, 2026Updated 7 months ago
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,059Apr 23, 2026Updated 6 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- vLLM TurboQuant☆619Jun 25, 2026Updated 4 months ago
- QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead☆98Jan 27, 2025Updated last year
- Port of Facebook's LLaMA model in C/C++☆22Aug 15, 2026Updated 3 months ago
- SimpleGrade – a minimal NumPy-based autograd and neural network framework for learning automatic differentiation and basic deep learning …☆13Aug 12, 2026Updated 3 months ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆870Aug 4, 2026Updated 3 months ago
- LLM inference in C/C++☆2,451Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,238Aug 18, 2026Updated 2 months ago
- Library for Google's Turboquant Algorithm☆69Mar 29, 2026Updated 7 months ago
- Running a big model on a small laptop☆4,521Mar 19, 2026Updated 7 months ago
- 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.
- AI agents running research on single-GPU nanochat training automatically☆100,083Mar 26, 2026Updated 7 months ago
- A vector index built on TurboQuant, written in Rust with Python bindings☆17,496Oct 7, 2026Updated last month
- ☆105Jul 19, 2026Updated 3 months ago
- Lucebox inference engine for heterogeneous hardware & consumer GPUs☆3,007Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆96,964Updated this week
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆204May 15, 2026Updated 6 months ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,367Updated this week
- High-Ratio Vector Quantization☆15Feb 3, 2026Updated 9 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,608Updated 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.
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆540Nov 26, 2024Updated last year
- 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.☆79,551Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,928Updated this week
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,625Updated this week
- ☆307Apr 5, 2026Updated 7 months ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆443Feb 14, 2025Updated last year
- ☆16Aug 28, 2025Updated last year
- Code and results for "Revisiting RaBitQ and TurboQuant: a symmetric comparison of methods, theory, and experiments".☆14Aug 1, 2026Updated 3 months ago
- Official inference framework for 1-bit LLMs☆41,584Jul 27, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Prototyp MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism☆35Apr 4, 2025Updated last year
- First MLX implementation of TurboQuant KV cache compression for Apple Silicon☆31Jun 2, 2026Updated 5 months ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆15,079Updated this week
- Fast and memory-efficient exact attention☆25,297Updated this week
- A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.☆14,927May 23, 2026Updated 5 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,899Updated this week
- Archived — ML Intern is no longer maintained. Continue with HuggingChat.☆10,783Oct 22, 2026Updated 3 weeks ago
Are these results useful?