llama.cpp Releases2026-10-16 08:18 UTC+8Original · English

[Pre-release / continuous build] b11671

[Pre-release / continuous build] model: add Muse Spark Open (text, vision and audio) (#30616) * model: add Muse Spark Open (text, vision and audio) Muse Spark Open is a latent space MoE: the residual stream stays at 8192…

Pre-release / continuous build: this is an experimental build, not a stable release.

model: add Muse Spark Open (text, vision and audio) (#30616) * model: add Muse Spark Open (text, vision and audio) Muse Spark Open is a latent space MoE: the residual stream stays at 8192 while the 256 experts live in 4096, with a projection down and up around them, top-8 sigmoid routing with a correction bias. Attention interleaves three sliding layers at a 2048 window with rope for one global layer without rope, with a sigmoid output gate and a weightless QK-norm. Residuals are norm preserving, their gate is folded at conversion time. Vision reuses the Muse Glimmer tower. Audio is a causal convolutional pyramid with no attention and no spectrogram, four stages folding 16, 6, 5 and 4 samples into the channel dim, one embedding per 80 ms of 24 kHz. The quantizer keeps the latent projections and the attention gate at Q8_0, a little over 1% of the weights, since the whole residual stream passes through them and the low-bit types turned the output into a repeating loop. The model saver writes the post norm epsilon, and the arch is registered in test-llama-archs. Co-authored-by: Xuan Son Nguyen Co-authored-by: Pedro Cuenca * Muse Spark: drop the redundant forward expand * Muse Spark: drop the redundant forward expand and tighten the comments * Update src/llama-quant.cpp Co-authored-by: Sigbjørn Skjæret * Update src/llama-graph.cpp Co-authored-by: Sigbjørn Skjæret * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret --------- Co-authored-by: Xuan Son Nguyen Co-authored-by: Pedro Cuenca Co-authored-by: Sigbjørn Skjæret

Website: - https://llama.app

Attestations: - https://github.com/ggml-org/llama.cpp/attestations/56481361

macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework

Linux: - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries - Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries - Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries - Ubuntu x64 (ROCm 10.0) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) - Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide