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.
☆1,038Apr 23, 2026Updated 3 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☆1,713Mar 27, 2026Updated 4 months ago
- Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (…☆26May 31, 2026Updated 2 months ago
- ☆7,003Jul 20, 2026Updated 2 weeks ago
- ☆201Apr 5, 2026Updated 3 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…☆1,043Apr 23, 2026Updated 3 months ago
- 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.
- vLLM TurboQuant☆611Jun 25, 2026Updated last month
- 12-episode video series teaching ML engineering by building real projects☆27Apr 20, 2026Updated 3 months ago
- QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead☆100Jan 27, 2025Updated last year
- First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression …☆78May 25, 2026Updated 2 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,562May 10, 2026Updated 2 months ago
- LLM inference in C/C++☆2,226Updated this week
- Python implementation of TurboQuant (arXiv 2504.19874). Data-oblivious, near-optimal 1–4 bit vector quantization for streaming KV-caches …☆21Mar 29, 2026Updated 4 months ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆836Jul 14, 2026Updated 3 weeks ago
- Running a big model on a small laptop☆4,039Mar 19, 2026Updated 4 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official Implementation For PolarQuant☆46Apr 2, 2026Updated 4 months ago
- T-Class 2.0: The Standard Framework for AI Sovereignty and Technical Independence☆19Jan 5, 2026Updated 6 months ago
- ☆103Jul 19, 2026Updated 2 weeks ago
- AI agents running research on single-GPU nanochat training automatically☆92,887Mar 26, 2026Updated 4 months ago
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,712Updated this week
- 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 4 months ago
- High-Ratio Vector Quantization☆15Feb 3, 2026Updated 6 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,085Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆3,377Updated 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.
- 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
- A vector index built on TurboQuant, written in Rust with Python bindings☆14,599Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,000Updated this week
- ☆16Aug 28, 2025Updated 11 months ago
- SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression☆200May 15, 2026Updated 2 months ago
- Official inference framework for 1-bit LLMs☆39,809Jul 27, 2026Updated last week
- ☆24Mar 26, 2026Updated 4 months ago
- 🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models☆10,709Updated this week
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,496Mar 19, 2026Updated 4 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.
- Bonsai Demo☆2,149Updated this week
- Kakao Mobility MCP Server for directions and transit information☆11Sep 14, 2025Updated 10 months ago
- A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.☆14,765May 23, 2026Updated 2 months ago
- ☆259Apr 5, 2026Updated 3 months ago
- TurboQuant reference implementation — KV cache compression with engineering insights (ICLR 2026 paper reproduction)☆17Mar 28, 2026Updated 4 months ago
- LLM inference in C/C++☆122,564Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,090Updated this week