ggerganov/llama.cpp b9330: b9330
extract
<details open> model: tag ffn_latent as MUL_MAT to fix buft probe (#23664) ffn_latent_down/up are declared GGML_OP_MUL in LLM_TENSOR_INFOS but nemotron-h feeds them through ggml_mul_mat. The loader buft probe asks the backend about the declared op, so it tested an elementwise MUL on a q8_0 weight. That used to return true unconditionally and the weight stayed on GPU by luck. Once supports_op told the truth, the probe got a no and the loader pushed the weight and its matmul to CPU, splitting the graph. Tagging it MUL_MAT asks the real question, the math is unchanged. Verified on Nemotron 3 Super 120B Q5_K_M: from 64.9 back to 103.22 t/s. </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-macos-arm64-kleidiai.tar.gz) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-openvino-2026.0-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-ubuntu-sycl-fp16-x64.tar.gz) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-cpu-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9330/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9330/cudart-llama-bin-win-cuda-13.1-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-vulkan-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-sycl-x64.zip) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-win-hip-radeon-x64.zip) **openEuler:** - [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-310p-openEuler-x86.tar.gz) - [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-910b-openEuler-x86-aclgraph.tar.gz) - [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-310p-openEuler-aarch64.tar.gz) - [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-bin-910b-openEuler-aarch64-aclgraph.tar.gz) **UI:** - [UI](https://github.com/ggml-org/llama.cpp/releases/download/b9330/llama-b9330-ui.tar.gz)
retained text
No document body was retained for this record — only its metadata was stored.