AMD said its Instinct MI350X and MI355X GPUs support Meta's Muse Spark Open on ROCm and vLLM, with BF16, MXFP4 and FP8 variants.
AMD said on Thursday it has added day-0 support for Meta's Muse Spark Open on Instinct MI350X and MI355X GPUs using ROCm software and vLLM, positioning the stack for a large open-weight model aimed at coding and long-running reasoning tasks.
In the technical article published Oct. 15, 2026, AMD described Muse Spark Open as the first open-weight model in the Muse Spark family and said it is a natively multimodal Mixture-of-Experts model with 816 billion total parameters, 42 billion active per token and a 1 million-token context window. AMD said the model includes configurable reasoning and native tool calling, and that it is available on Hugging Face, Muse Code, the Meta Model API and OpenRouter.
AMD said the model can run on a single node of eight Instinct MI350X or MI355X GPUs, with 288 GB of HBM3E per GPU and 8 TB/s memory bandwidth, using tensor parallelism across eight GPUs. The company said the software stack is ROCm 7.2 with vLLM, along with the AMD AITER kernel library for attention, MoE and communication, and CUDA-graph capture for the decode step.
The article listed three supported checkpoints for vLLM: a BF16 open release, an MXFP4 AMD Quark export and an FP8 AMD Quark export using PTPC. AMD said the BF16 checkpoint can also be served with an opt-in mode that rounds routed experts to MXFP4 at load time, giving the MXFP4 memory and throughput profile without a separate checkpoint.
Source link
