TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
☆1,814Sep 3, 2026Updated 2 months ago
Alternatives and similar repositories for turboquant
Users that are interested in turboquant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM TurboQuant☆619Jun 25, 2026Updated 4 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…☆1,048Apr 23, 2026Updated 6 months ago
- ☆7,024Jul 20, 2026Updated 3 months ago
- ☆200Apr 5, 2026Updated 6 months ago
- LLM inference in C/C++☆2,440Oct 22, 2026Updated last week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,210Aug 18, 2026Updated 2 months ago
- A vector index built on TurboQuant, written in Rust with Python bindings☆17,455Oct 7, 2026Updated 3 weeks 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…☆1,058Apr 23, 2026Updated 6 months ago
- Experimental llama.cpp fork for inference research and development☆896Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆96,053Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,253Updated 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.☆78,910Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,277Jul 9, 2026Updated 3 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,488Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.☆405Apr 26, 2026Updated 6 months ago
- AI agents running research on single-GPU nanochat training automatically☆99,076Mar 26, 2026Updated 7 months ago
- ☆308Apr 5, 2026Updated 6 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,342Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,838Oct 26, 2026Updated last week
- The agent that grows with you☆259,405Updated this week
- AirLLM 2.8T LLM inference with single 4GB GPU☆41,525Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,970Updated this week
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆440Feb 14, 2025Updated last year
- 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.
- OpenShell is the safe, private runtime for autonomous AI agents.☆20,922Updated this week
- Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦☆46,528Updated this week
- A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.☆14,920May 23, 2026Updated 5 months ago
- ☆511Apr 8, 2026Updated 6 months ago
- State-of-the-art LLM compression, built for production inference with vLLM☆3,937Updated this week
- Experimental Rust vector-compression sidecars implementing TurboQuant (ICLR 2026), PolarQuant and QJL research primitives, with exact rer…☆27Oct 25, 2026Updated last week
- an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM☆56,072Updated this week
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆16,056Updated this week
- Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference☆22,904Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG☆39,937Updated this week
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆867Aug 4, 2026Updated 2 months ago
- LLM inference in C/C++☆133,099Updated this week
- A self-improving RLM agent for coding workflows and long-running autonomous tasks.☆22,486Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,841Updated this week
- QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead☆98Jan 27, 2025Updated last year
- Official inference framework for 1-bit LLMs☆41,441Jul 27, 2026Updated 3 months ago