XTU = X Transformers Unity — hybrid (CPU-expert + GPU) inference acceleration for vLLM: mainline plugin + CPU MoE engine (AVX512-VNNI/BF16 MXFP4/FP8), long-prefill GPU streaming, SM80 (A100) port.
☆16Nov 2, 2026Updated last week
Alternatives and similar repositories for Xiaotu-LLM
Users that are interested in Xiaotu-LLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A tool for USB device pass-through using the vfio-user protocol.☆49Updated this week
- Phoenix++ converted to use multiple processes☆11Feb 17, 2022Updated 4 years ago
- A LaTeX template for theses☆18Jun 18, 2026Updated 4 months ago
- Cross-tier CPU/GPU hybrid MoE inference for SGLang (plugin, tracks upstream main)☆72Updated this week
- Scribe Handler for python logging☆14Apr 20, 2012Updated 14 years 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.
- DSH 运维工具箱：升级、重启、故障都不用操心。① 官方每日快照 A/B 双槽轮换——旧插件迁移+构建+验收全过才原子切换，一键回滚，旧版本永远兜底；② 守护 10s 自动拉起 web + agent 断点自动续接，重启无人值守；③ web 全挂（A/B 都坏、agent …☆17Oct 30, 2026Updated last week
- Live subtitles with translation using stream API for macOS☆14Aug 3, 2026Updated 3 months ago
- Example programs for Parallella☆18Jul 11, 2014Updated 12 years ago
- Pusher++ is a header-only cross-platform C++ library for connecting to Pusher☆18Jan 25, 2018Updated 8 years ago
- ☆21May 15, 2026Updated 5 months ago
- Some of my useful hazel rules☆27Nov 28, 2012Updated 13 years ago
- 按快捷键，说话，说完自动识别并上屏 —— 基于大模型的流式语音识别（ASR）的 Linux 语音输入工具☆18Aug 20, 2026Updated 2 months ago
- Agnost GitOps Helm charts☆13Dec 9, 2025Updated 11 months ago
- Yet another codex remote in feishu☆18Oct 24, 2026Updated 2 weeks ago
- 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.
- The HWaaS is a reproducible hardware-in-the-loop testing platform for shared hardware leases, enabling development, testing, and CI/CD pi…☆50Updated this week
- Agent Skills for Xmake☆25Aug 23, 2026Updated 2 months ago
- Distillation pipeline from pretrained Transformers to customized FLA models☆13Aug 4, 2025Updated last year
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆168Updated this week
- trace clojure call stack☆27Feb 2, 2013Updated 13 years ago
- Get more sleep with Sleeper!☆14Mar 9, 2024Updated 2 years ago
- In this project we try to create a sophisticated computer agent to play the Contact Bridge card game. Our goal is to develop an agent tha…☆20Aug 22, 2020Updated 6 years ago
- Tries to UI development. Clone of https://www.perplexity.ai/☆11Sep 30, 2023Updated 3 years ago
- Scripts to setup a two-node llama.cpp cluster on NVIDIA DGX Spark (GB10) hardware.☆12May 10, 2026Updated 6 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.
- A minimalist webpage for installing fonts on iOS / iPadOS devices☆13Jan 16, 2025Updated last year
- SSL VPN☆23Jul 20, 2023Updated 3 years ago
- DeepSeek 41 Flash local inference engine for Metal and CUDA☆19Nov 2, 2026Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆13Apr 14, 2026Updated 6 months ago
- GPU peer-to-peer over dynamic BAR1 for GeForce cards: patched NVIDIA open kernel modules.☆19Nov 6, 2026Updated last week
- CLI App that acts as a wallet☆30Aug 15, 2018Updated 8 years ago
- ☆14Sep 4, 2024Updated 2 years ago
- AMD PACE is a PyTorch extension for high-performance LLM inference on AMD CPUs. It provides a framework to develop and test novel optimiz…☆17Oct 21, 2026Updated 3 weeks ago
- Bypass iOS version check for apps in the AppStore☆15Sep 3, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- The most advanced and feature rich system wide haptic feedback tweak☆12May 10, 2025Updated last year
- A Philosophy of Software Design 《软件设计的哲学》中文翻译☆19Aug 11, 2026Updated 3 months ago
- 64bit PC emulator and x64-to-wasm JIT, running in the browser☆29Updated this week
- Hackintosh - MSI B360m Mortar for OpenCore☆15Jun 20, 2026Updated 4 months ago
- REST extension for Emmett framework☆18Oct 14, 2024Updated 2 years ago
- 北邮云课堂签到☆12Sep 29, 2026Updated last month
- High-performance macOS Wi-Fi driver for Realtek RTL8922AE (Wi-Fi 7) & RTW89 PCIe cards with 200Mbps+ symmetric throughput.☆20Oct 21, 2026Updated 3 weeks ago
Are these results useful?