Havuz

Strata 0.2.3 (engine 0.1.48) for AMD gfx906 (MI50/MI60/Radeon VII): rocBLAS solution table, Qwen3.6/Ornith engine restored, DFlash2 build fi

WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Ra

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next. Th

halogen-flash-server, Qwen3.8-Flash-Next modelini AMD Strix Halo (gfx1151) donanımında çalıştırmak için özelleştirilmiş bir inference server'dır.

Neden yükseliyor · 32 günlük repo için 722 yıldız ve son 28 günde 99 commit dikkat çekiyor. README, belirli donanım üzerindeki ölçümleri ve ölçüm koşullarını açıklıyor; ancak performans iddiaları proje tarafından sunulmuş ve bağımsız doğrulama bilgisi burada yok. 99 commit'in tek yazardan gelmesi geliştirme hızını gösterirken bakım kapasitesine dair kanıtı sınırlıyor.

The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)

AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NP

HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.

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

DeepSeek-V4-Flash inference for AMD Strix Halo

See every GPU in your lab in the terminal, the browser or a report — who holds each GPU, which ones sit idle. One Python file, nothing to in

Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.

Instella MoE is a fully open state-of-the-art Mixture-of-Experts language model, trained end-to-end on AMD Instinct™ GPUs.

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Hardware-aware post-install for Fedora 45 KDE Plasma 6 on Wayland: NVIDIA, AMD or Intel, desktop or laptop, dual-boot. Low-latency gaming, K

Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.

Whisper-large-v3 fine-tune for Indonesian + Javanese + Sundanese ASR. Lhotse + k2 lattice rescoring pipeline.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

Browser-based operator console for managing and monitoring Lemonade on Linux inference servers.

Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)

Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.

SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)

DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2

LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板