llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.
☆41Jul 2, 2026Updated 2 weeks ago
Alternatives and similar repositories for llama-cpp-turboquant
Users that are interested in llama-cpp-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:
- ☆12Jul 6, 2026Updated last week
- LLM inference in C/C++☆2,104Updated this week
- LLM inference in C/C++☆63May 7, 2026Updated 2 months ago
- ☆140Jun 13, 2026Updated last month
- Community-maintained fork of the classic Python Open Interpreter. The classic/develop branch is what I use on a regular basis, and it ha…☆23Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Semreh V2 line-follower robot code.☆15Feb 8, 2025Updated last year
- Fork of turbo quant tom-tom and TurboQuant KV cache from domwox☆29Jul 7, 2026Updated last week
- An RP2040 stamp supporting in-system-programming via Tag-Connect.☆12Oct 24, 2022Updated 3 years ago
- Pico Pal GBC V4 & V5 Firmware with RP2350B☆40Apr 11, 2026Updated 3 months ago
- MusiqPad server for hosting your pads☆15Nov 23, 2021Updated 4 years ago
- My Pi extensions☆15Jun 19, 2026Updated 3 weeks ago
- AceForge is a local-first AI music workstation for Apple/OSX based on Ace-Step, DeMucs, XTTSv2☆85Feb 11, 2026Updated 5 months ago
- DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM☆777Updated this week
- Fix broken dev servers instantly. A fast Rust CLI for port conflicts, zombie processes, and dev server recovery.☆15Apr 8, 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.
- 开源网址导航☆13Apr 15, 2021Updated 5 years ago
- simple tint identifier☆14Jul 21, 2024Updated last year
- 带后台点击的，已经汉化过的鼠标点击器☆30Oct 17, 2025Updated 8 months ago
- ☆10Aug 10, 2015Updated 10 years ago
- A common protocol for AI agent tools☆10Oct 21, 2024Updated last year
- CSS3与页面布局学习总结（一）——概要、选择器、特殊性与刻度单位☆14Nov 24, 2016Updated 9 years ago
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆301Jul 4, 2026Updated last week
- .Net访问微信公共平台接口☆28May 11, 2015Updated 11 years ago
- MacOS dragging helper☆12Mar 31, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Extract structured data from documents, images, audio, and video using LLMs.☆18Updated this week
- Memo's Blog☆27Jan 21, 2026Updated 5 months ago
- Train small sequence models in your browser with WebGPU.☆35Dec 3, 2025Updated 7 months ago
- Zig implementation of Apache Arrow☆15Jun 14, 2026Updated last month
- fpga i2c rtc oled based clock with alarm supports buzzer☆16May 15, 2021Updated 5 years ago
- A simple 'Space Shooter' game written on an STM32L4 with a 128X128 OLED display based on the SSD1327 controller.☆33Feb 2, 2026Updated 5 months ago
- A mod that allows you to add/replace existing files without repacking CRI Middleware CPKs.☆14Jun 14, 2026Updated last month
- Implementations of UUID v4 and v7 as defined in the lastest RFC4122 draft. Including a highly-performant custom UUID v8 implementation.☆12May 27, 2025Updated last year
- ☆11Nov 29, 2023Updated 2 years ago
- 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.
- Docker container for use with Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch☆10Jan 19, 2019Updated 7 years ago
- Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on t…☆26May 8, 2026Updated 2 months ago
- Seamless Voice Interactions with LLMs☆12Oct 28, 2023Updated 2 years ago
- ☆13Aug 5, 2024Updated last year
- A snes9x port running on the ESP32-P4 based on retro-go☆40Mar 22, 2026Updated 3 months ago
- Use comboclean to make it easy to use email and passwords, from big combolists, in your script.☆15Aug 27, 2021Updated 4 years ago
- [AAAI'23] FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction https://arxiv.org/abs/2304.00902☆11Apr 9, 2023Updated 3 years ago