b10016
ggml-org/llama.cppb10016Jul 15, 2026by github-actions[bot]
AI Summary
Introduces Flash Attention support for the SYCL backend using the XMX engine and oneDNN graph API, significantly improving prefill speeds on Battlemage architecture.
Key Highlights
- SYCL Flash Attention with XMX engine via oneDNN graph API
- Significant speedup: x1.21 at p=512 and x4.26 at p=80k for Qwen3.6-27b
- Focused on Battlemage (BMG) architecture with multi-device sync support
New Features
- SYCL Flash Attention with XMX engine
Full Release Notes
<details open> [SYCL] Flash Attention with XMX engine via oneDNN (#25222) * [SYCL] F16 (default) Flash Attention with XMX engine via oneDNN graph API; Qwen3.6-27b-Q8_0 prefill speed up x1.21 at p=512 and x4.26 at p=80k * [SYCL] Address review on FA oneDNN path. Result: llama-bench---pp512; 32% increase with fa1; llama-perplexity---0.11% difference; tested model: mradermacher/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf * PR-25222 revision v2: addressed audits * [SYCL] flash-attn oneDNN SDPA KV F16 rev 3.0: add BMG gate + multi-device sync. Narrow the scrope of this PR to Battlemage only (bmg; Xe2). Other archs (e.g., alchemist) fall back to existing FA kernel. When device_count >1, apply stream -> wait_and_throw(), validated working path for multi-gpu sync fix by @maxious. Co-authored-by: maxious <81432+maxious@users.noreply.github.com> * updated comment on bmg gate, noted the issue --------- Co-authored-by: scientist3 <scientist.3@users.noreply.github.com> Co-authored-by: hmscider <hmscider@users.noreply.github.com> Co-authored-by: maxious <81432+maxious@users.noreply.github.com> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-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/b10016/llama-b10016-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-openvino-2026.2.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-ubuntu-sycl-fp16-x64.tar.gz) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10016/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10016/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-vulkan-x64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-openvino-2026.2.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-sycl-x64.zip) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10016/llama-b10016-bin-win-hip-radeon-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/b10016/llama-b10016-ui.tar.gz)