Stars
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and …
halo-box / strix-llama.cpp
Forked from halo-box/llama.cppLLM inference in C/C++
Nathanw1014 / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
High-fidelity, browser-native PPTX renderer in TypeScript. Parses OOXML into HTML/SVG DOM with rich text, shapes, images, tables, 2D charts, SmartArt, equations, effects, and bounded static Drawing…
High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, RDNA3), Vulkan backend for consumer GPUs. No CUDA required.
A middleware proxy that manages chain-of-thought reasoning for GPT-OSS models.
lemon07r / pampax
Forked from tecnomanu/pampaProtocol for Augmented Memory of Project Artifacts (MCP compatible) - extended
Helps agents work more efficiently by translating cline/Roo-Code tool calls into native tool calls in the API
Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and <think> tag filtering. Perfect for using advanced models wi…
Reliable model swapping for any local AI server. Chosen by thousands of users. Batteries included. If we don't have it, you probably don't need it.