b9767 버전 릴리스 노트

ggml-webgpu: 소규모 배치(small batches)에 mat-vec 경로를 사용하여 MTP 추론 개선 (#24811)

• ggml-webgpu: 소규모 배치 디코딩 개선

• mul-mat-vec에서 NUM_COLS 루프에 배리어(barrier) 추가

macOS/iOS:

• macOS Apple Silicon (arm64)
• macOS Apple Silicon (arm64, KleidiAI 활성화) 비활성화됨
• macOS Intel (x64)
• iOS XCFramework

Linux:

• Ubuntu x64 (CPU)
• Ubuntu arm64 (CPU)
• Ubuntu s390x (CPU)
• Ubuntu x64 (Vulkan)
• Ubuntu arm64 (Vulkan)
• Ubuntu x64 (ROCm 7.2)
• Ubuntu x64 (OpenVINO)
• Ubuntu x64 (SYCL FP32)
• Ubuntu x64 (SYCL FP16)

Android:

Android:

• Android arm64 (CPU)

Windows:

• Windows x64 (CPU)
• Windows arm64 (CPU)
• Windows arm64 (OpenCL Adreno)
• Windows x64 (CUDA 12) - CUDA 12.4 DLLs
• Windows x64 (CUDA 13) - CUDA 13.3 DLLs
• Windows x64 (Vulkan)
• Windows x64 (OpenVINO)
• Windows x64 (SYCL)
• Windows x64 (HIP)

openEuler:

• DISABLED
• openEuler x86 (310p)
• openEuler x86 (910b, ACL Graph)
• openEuler aarch64 (310p)
• openEuler aarch64 (910b, ACL Graph)

UI:

• UI