AISpot

llama.cpp 的 OpenCL 後端初步支援 IQ3 量化

llama.cpp releases版本更新地端推論開源

llama.cpp 的 OpenCL 後端加入對 IQ3 量化的初步支援,覆蓋 iq3_s 與 iq3_xxs 兩種型別。這批提交為 Adreno GPU 補齊了 AOS/SOA 矩陣向量乘、tiled 矩陣乘、noshuffle 的 GEMM/GEMV 與 dp4a 路徑,並最佳化了 Adreno 上的解碼與窄 batch 場景。改動由高通工程師參與合入,建置產物中已包含 Windows arm64 OpenCL Adreno 版本。

原標題:b12031
閱讀原文

評分48 / 50(平均 49,門檻 60)
狀態未入選

原文

opencl: add initial iq3 support ( #31338 ) opencl: add iq3_s AOS mv Assisted-by: Codex opencl: add iq3_s SOA mv and tiled mm Assisted-by: Codex opencl: add iq3_s noshuffle gemm/gemv for adreno Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex opencl: add iq3_s dp4a for adreno Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex opencl: optimize iq3_s adreno decode and narrow batches Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex opencl: add iq3_xxs AOS mv Assisted-by: Codex opencl: add iq3_xxs SOA mv and tiled mm Assisted-by: Codex opencl: add iq3_xxs noshuffle gemm/gemv for adreno Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex opencl: add iq3_xxs dp4a for adreno Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex opencl: optimize iq3_xxs adreno decode and narrow batches Co-authored-by: Shaofei Qi [email protected] Assisted-by: Codex Co-authored-by: Li He [email protected] Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/62283042 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 26.04 s390x (CPU) Ubuntu 26.04 s390x (zDNN) 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 releases● 精選AI 評分63

llama.cpp 的 OpenCL 後端新增 IQ2 系列量化,並針對 Adreno GPU 最佳化

llama.cpp 的 OpenCL 後端首次加入對 IQ2 系列 2-bit 量化(iq2_s、iq2_xs、iq2_xxs)的支援,並針對高通 Adreno GPU 做了專項最佳化。提交為每種量化型別補上了 AOS/SOA 矩陣向量乘、tiled matmul、noshuffle 的 GEMM/GEMV 與 dp4a 路徑,並最佳化了 Adreno 上的 decode 與窄批次場景。