ggerganov/llama.cpp b9088: b9088
extract
<details open> [SYCL] Add BF16 support to GET_ROWS operation (#21391) Add GGML_TYPE_BF16 to the SYCL backend's GET_ROWS operation, both in supports_op and in the kernel dispatch. This fixes a performance regression where models using BF16 embedding tensors (e.g., Gemma4's per_layer_token_embd.weight) fall back to CPU for the GET_ROWS op, causing a full GPU-to-CPU tensor transfer every token. The fix reuses the existing get_rows_sycl_float template with sycl::ext::oneapi::bfloat16, matching the pattern already used for sycl::half (F16) and float (F32). </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-macos-arm64-kleidiai.tar.gz) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-openvino-2026.0-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-ubuntu-sycl-fp16-x64.tar.gz) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-cpu-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9088/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9088/cudart-llama-bin-win-cuda-13.1-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-vulkan-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-sycl-x64.zip) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-win-hip-radeon-x64.zip) **openEuler:** - [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-310p-openEuler-x86.tar.gz) - [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-910b-openEuler-x86-aclgraph.tar.gz) - [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-310p-openEuler-aarch64.tar.gz) - [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9088/llama-b9088-bin-910b-openEuler-aarch64-aclgraph.tar.gz)
retained text
No document body was retained for this record — only its metadata was stored.