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.
☆1,047Apr 23, 2026Updated 5 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☆1,788Sep 3, 2026Updated last month
- Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (…☆26Updated this week
- ☆7,031Jul 20, 2026Updated 2 months ago
- ☆200Apr 5, 2026Updated 5 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…☆1,052Apr 23, 2026Updated 5 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☆618Jun 25, 2026Updated 3 months ago
- 12-episode video series teaching ML engineering by building real projects☆26Apr 20, 2026Updated 5 months ago
- Port of Facebook's LLaMA model in C/C++☆22Aug 15, 2026Updated last month
- Open-source implementation of Google's TurboQuant (ICLR 2026) — KV cache compression to 2.5–4 bits with near-zero quality loss. 3.8–5.7x …☆52Mar 29, 2026Updated 6 months ago
- LLM inference in C/C++☆2,414Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,131Aug 18, 2026Updated last month
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆854Aug 4, 2026Updated last month
- Python implementation of TurboQuant (arXiv 2504.19874). Data-oblivious, near-optimal 1–4 bit vector quantization for streaming KV-caches …☆20Mar 29, 2026Updated 6 months ago
- Running a big model on a small laptop☆4,199Mar 19, 2026Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆103Jul 19, 2026Updated 2 months ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,887Updated this week
- AI agents running research on single-GPU nanochat training automatically☆97,133Mar 26, 2026Updated 6 months ago
- High-Ratio Vector Quantization☆15Feb 3, 2026Updated 8 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆93,064Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,164Updated this week
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.☆77,128Updated this week
- A vector index built on TurboQuant, written in Rust with Python bindings☆17,269Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,946Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆16Aug 28, 2025Updated last year
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆203May 15, 2026Updated 4 months ago
- Official inference framework for 1-bit LLMs☆40,355Jul 27, 2026Updated 2 months ago
- Bonsai Demo☆3,251Updated this week
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,577Mar 19, 2026Updated 6 months ago
- Archived — ML Intern is no longer maintained. Continue with HuggingChat.☆10,810Updated this week
- Kakao Mobility MCP Server for directions and transit information☆11Sep 14, 2025Updated last year
- A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.☆14,903May 23, 2026Updated 4 months ago
- ☆307Apr 5, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out…☆49Aug 5, 2026Updated last month
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆432Feb 14, 2025Updated last year
- TurboQuant reference implementation — KV cache compression with engineering insights (ICLR 2026 paper reproduction)☆17Mar 28, 2026Updated 6 months ago
- LLM inference in C/C++☆130,140Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,532Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,718Updated this week
- Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦☆38,992Updated this week