Stars
Private Strata customizations for 9950x3d2+dual 7900xtx; upstream Niko1221/Strata
Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Fast local LLM inference on AMD Radeon RX 7900 XTX / XT (RDNA3, ROCm): big Mixture-of-Experts models like Qwen3.8-Flash-Next on one or two consumer GPUs. Up to 4 parallel agents with 262k context e…
Run MoE models beyond VRAM on AMD, NVIDIA & Intel GPUs. Vulkan-powered, portable Windows app with automatic setup. | 让游戏显卡跑起超显存大模型，支持 AMD、NVIDIA、Intel，免安装、自动配置。只需13MB，即下即用！
The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
Hiqlite - highly-available, embeddable, raft-based SQLite + cache
🚀 Apache RocketMQ built in Rust 🦀 — faster, safer, and more memory-efficient. Powering high-performance messaging for the AI era, with AI Agent, MCP, and AI-SRE capabilities.
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
Reproducible, evidence-backed llama.cpp serving recipes for Strix Halo class machines — annotated parameters, ▏ multi-witness results, agent-first tooling.
pwilkin / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
A fast & densely stored hashmap and hashset
halo-box / strix-llama.cpp
Forked from halo-box/llama.cppLLM inference in C/C++
Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.
Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.
Fast stackful fibers with a NUMA-aware work-stealing scheduler
Bot that bridges Feishu/Lark messenger with a local Claude Code or Codex CLI. Streaming cards, per-chat sessions, multiple workspaces
A high-performance, persisted Key-Value storage based on C++20 and io_uring
A fast multi-producer, multi-consumer lock-free concurrent queue for C++11
韩先凯的人生进阶指南 AI时代 中英双语终身学习指南：AI、学习 、创业、财富、爱情与人生
A modern framework for backend development based on io_uring Linux interface
跨平台中国软件著作权源代码收集器 （GUI图形界面/ 软著自动收集 / 60页源码 / 自动生成 World文档）
Efficient reliable UDP unicast, UDP multicast, and IPC message transport
A simple to deploy but feature rich S3 object storage server for your filesystem