<details open> opencl: fix three defects of the bin flash-attention prefill path (#32110) * opencl: release the WMM flash-attention mask fallback image The fallback image is created on every call of the bin flash-attention kernel over a sub-buffer of the K cache and was never released, so each call kept a K-cache sub-buffer alive. Every call with more than one query row takes this path, including each speculative-decoding verify step, so the objects pile up and the server slows with every request. * opencl: keep q8_0 K/V at head size 512 off the WMM flash-attention kernel With q8_0 K/V at DK=512 the bin flash-attention kernel gives wrong results whenever V holds different values from K (test-backend-ops FLASH_ATTN_EXT hsk=512 q8_0, max error 2.04 on X2-90); f16 K/V at DK=512 is correct. The backend's own flash-attention kernels already decline q8_0 at DK=512, so the shape is now handled the same way with or without the kernel library. * opencl: decline WMM flash-attention prefill beyond the device's 3D image limits The WMM path repacks Q/K/V into 3D images; V is n_kv wide, so past the device's maximum 3D image width (about 16k tokens of context on X2-90) clCreateImage failed and the call asserted. Such shapes now take the regular flash-attention path. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/68465218> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-arm64.tar.gz) - [Ubuntu 24.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-s390x.tar.gz) - [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-26.04-s390x.tar.gz) - [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-zdnn-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-b12456-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-cuda-13.5-x64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-b12456-bin-ubuntu-cuda-13.5-x64.tar.gz) - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-b12456-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-rocm-10.0-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-openvino-2026.4.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-ubuntu-sycl-fp16-x64.tar.gz) - [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-android-arm64.tar.gz) - [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-cuda-13.5-x64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-bin-win-cuda-13.5-x64.zip) - [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-cuda-13.5-arm64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12456/cudart-llama-bin-win-cuda-13.5-arm64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-vulkan-x64.zip) - [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-vulkan-arm64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-openvino-2026.4.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-sycl-x64.zip) - [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-bin-win-rocm-10.0-x64.zip) **openEuler:** - [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - openEuler x86 (310p) - openEuler x86 (910b, ACL Graph) - openEuler aarch64 (310p) - openEuler aarch64 (910b, ACL Graph) **UI:** - [UI](https://github.com/ggml-org/llama.cpp/releases/download/b12456/llama-b12456-ui.tar.gz)
AI NEWS JOURNAL
llama.cpp releasesAI NEWS / JOURNAL
b12456
The update addresses three issues in the OpenCL implementation of the bin flash-attention prefill path: releasing a previously unreleased WMM flash-attention mask fallback image, excluding q8_0 K/V at head size 512 from the WMM kernel due to incorrect results, and preventing the use of the WMM path beyond device 3D image limits to avoid clCreateImage failures.
번역 서비스가 일시 중지되어 원문을 표시합니다.