Red-Weasel/machx-inference-engine
C++/SYCL local LLM inference for Intel Arc: Qwen3.8, DeepSeek-V4.1, MiMo-V2.6, GLM-5.3 and LTX-2.5 text-to-video on Arc Pro B70 cards. XMX kernels, quantized models, multi-GPU.
GitHub repository with 9 stars and 2 forks.
Language: C++
Topics: battlemage, gguf, gpu, inference-engine, intel-arc, llm, oneapi, quantization, sycl, tensor-parallel