TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
☆1,721Mar 27, 2026Updated 4 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☆612Jun 25, 2026Updated last month
- 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
- ☆200Apr 5, 2026Updated 4 months ago
- ☆7,003Jul 20, 2026Updated 3 weeks ago
- LLM inference in C/C++☆2,250Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,579May 10, 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…☆1,044Apr 23, 2026Updated 3 months ago
- A vector index built on TurboQuant, written in Rust with Python bindings☆14,707Updated this week
- LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.☆397Apr 26, 2026Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,592Updated this week
- Experimental llama.cpp fork for inference research and development☆731Updated this week
- The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.☆69,824Updated this week
- AI agents running research on single-GPU nanochat training automatically☆93,498Mar 26, 2026Updated 4 months ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,093Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (…☆26May 31, 2026Updated 2 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,638Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆6,915Jul 9, 2026Updated last month
- The agent that grows with you☆228,016Updated this week
- ☆584Jul 27, 2026Updated 2 weeks ago
- QJL: 1-Bit Quantized JL transform for KV Cache Quantization with Zero Overhead☆100Jan 27, 2025Updated last year
- ☆501Apr 8, 2026Updated 4 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,578Updated this week
- A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.☆14,794May 23, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM☆52,604Updated this week
- OpenShell is the safe, private runtime for autonomous AI agents.☆8,080Updated this week
- AirLLM 70B inference with single 4GB GPU☆30,571Updated this week
- Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference☆22,112Updated 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
- ☆402Jul 30, 2026Updated last week
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,728Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆3,418Updated this week
- OBLITERATE THE CHAINS THAT BIND YOU☆7,379Jun 17, 2026Updated last month
- 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.
- LLM inference in C/C++☆123,235Updated this week
- The open-source app everyone uses to manage agents at work☆76,473Updated this week
- ☆259Apr 5, 2026Updated 4 months ago
- Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cu…☆104,672Updated this week
- AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI☆86,656Updated this week
- Official inference framework for 1-bit LLMs☆39,953Jul 27, 2026Updated 2 weeks ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆841Aug 4, 2026Updated last week