ggerganov/llama.cpp b9368: b9368
extract
<details open> vulkan: Switch MUL_MAT_VEC to 4 K per iteration for F16/32 (#22887) * vulkan: Switch MUL_MAT_VEC to 4 K per iteration for F16/32 Against mesa git, this shows a 4.8% performance improvement for tg128 on Qwen3.5-9B:BF16 on Intel BMG. Note that this breaks some tests until the last commit which fixes OOB A reads. * vulkan: Use aligned loads in mul_mat_vec when available Against mesa git, this shows a 3.3% performance improvement for tg128 on Qwen3.5-9B:BF16 on Intel BMG. * Make explicit that `num_rows` is <= `NUM_ROWS` in mul_mat_vec Mesa's UUB logic can't see through conditionals, limiting its ability to understand the bounds on the `num_rows` field in the cleanup run. Making it explicit that `num_rows` is, indeed, always <= `NUM_ROWS` helps mesa make slightly better codegen. Against mesa git, this currently shows a 1% performance improvement in tg128 on Qwen3.5-9B:BF16 on Intel BMG. * vulkan: Fix OOB A reads in MUL_MAT_VEC for odd sizes There was a TODO to fix the OOB reads from the A matrix which we do here. It is within performance noise (+<0.1%) in tg128 for Qwen3.5-9B:BF16 on Intel BMG. </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-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/b9368/llama-b9368-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-ubuntu-openvino-2026.0-x64.tar.gz) - Ubuntu x64 (SYCL FP32) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-win-cpu-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9368/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9368/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-bin-win-vulkan-x64.zip) - Windows x64 (SYCL) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9368/llama-b9368-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/b9368/llama-b9368-ui.tar.gz)
retained text
No document body was retained for this record — only its metadata was stored.