AISpot

llama.cpp OpenCL 後端新增多個小批次 GEMM 變體並修復越界讀

llama.cpp releases版本更新地端推論開源

llama.cpp 建置 b11763 為 OpenCL 後端補上多個面向小批次的 GEMM/GEMV 核心變體,並修復 mul_mv_mxfp4_f32_flat 的越界讀取。新增項包括 q4_k dp4a GEMM 的小批次變體、mul_mm_f16_f32_l4_lm 的窄化變體,以及大 M 時 gemv_noshuffle_q1_0_f32 的單 subgroup 變體,並按 workgroup 大小限制 q4_0 mc3 的 subgroup 數量。

原標題:b11763
閱讀原文

評分33 / 45(平均 39,門檻 60)
狀態未入選

原文

opencl: add several gemm variants for small batches and some fixes ( #30850 ) opencl: fix OOB read in mul_mv_mxfp4_f32_flat opencl: remove large-N guard that forces CPU weight placement this condition claims that large batch produces incorrect results on adreno and cannot be reproduced model loader uses N512 to probe op support, resulting in cpu fallback thus this condition does not seem necessary opencl: cap num of subgroups by workgroup size for q4_0 mc3 Co-authored-by: Hongqiang Wang [email protected] opencl: add small batch variant for q4_k dp4a GEMM Co-authored-by: Hongqiang Wang [email protected] opencl: add a narrow variant of mul_mm_f16_f32_l4_lm Co-authored-by: Hongqiang Wang [email protected] opencl: add a one subgroup variant for gemv_noshuffle_q1_0_f32 for big M Co-authored-by: Hongqiang Wang [email protected] Co-authored-by: Hongqiang Wang [email protected] Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/57990792 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries Ubuntu x64 (ROCm 10.0) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16) Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Android: Android arm64 (CPU) Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows arm64 (OpenCL Adreno) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.4 DLLs Windows arm64 (CUDA 13) - CUDA 13.4 DLLs Windows x64 (Vulkan) Windows arm64 (Vulkan) Windows x64 (OpenVINO) Windows x64 (SYCL) Windows x64 (ROCm 10.0) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

相關報導

llama.cpp releasesAI 評分45

llama.cpp 為 OpenCL 新增 cooperative-k dp4a GEMM

llama.cpp 建置 b11741 在 OpenCL 後端為 q4_0、q4_k、q6_k 三種量化格式加入 cooperative-k dp4a GEMM,並修復對齊問題。這意味著在 OpenCL 上執行這些 4bit、6bit 量化模型的裝置可以用上新的矩陣乘實現。該版本同時更新了 macOS、Linux、Windows、Android 多平台建置,覆蓋 CUDA 12/13、ROCm 10.0、Vulkan、SYCL 等後端。

llama.cpp releasesAI 評分42

llama.cpp 為 SYCL 後端加入分組 MoE XMX GEMM

llama.cpp 建置 b11493 為 SYCL 後端新增分組 MoE XMX GEMM 運算元(#29245),面向混合專家模型的矩陣乘加速。該版本同時放出全平台建置產物,覆蓋 macOS/iOS、Linux、Windows、Android 與 openEuler,包含 CUDA 12/13、ROCm 10.0、Vulkan、OpenVINO、SYCL FP32/FP16,以及 Snapdragon 的 CPU、Adreno GPU 與 Hexagon NPU 組合。