shawnshekari/strixite

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

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

LLM 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.

A high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60

Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell

llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx

This repository builds llama.cpp for Strix Halo devices.

C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer