Starstruk Logo MarkStarstruk

b10758

Pre-release

ggml-org/llama.cppb10758Sep 2, 2026by github-actions[bot]

AI Summary

Significant performance and stability improvements for Hexagon (Qualcomm) hardware, including kernel fusion and memory management optimizations.

Key Highlights

  • Fused QKV and FFN matmuls that land on HMX memory.
  • Removed the hardcoded ne[1] < 32K restriction.
  • Improved VTCM budget handling to prevent overflow.
  • Added buffer defragmentation to prevent VA space fragmentation.

Full Release Notes

<details open>

hexagon: MUL_MAT and MUL_MAT_ID fusion and fixes (#28202)

* hex-mm: fuse QKV and FFN matmuls that land on HMX

* hex-mm: remove hardcoded ne[1] < 32K restriction

* hex-get-rows: explicitly reject repacked Q8_0 just in case somebody decided to add an override

* hex-mm: correct overhead sizing to make sure we dont exceed vtcm budget for large dims

* hex-mm: fuse MUL_MAT_ID into MUL_MAT_ID_NX (2x,3x,...) where possible

* hex-fusion: update opbatch and opqueue sizing to acount for new fusion and reduce overhead for trace buffer alloc

* hex-bufs: sort buffers while finalizing opbatch, helps avoid va space fragmentation

* hex-bufs: add simple va defrag to make sure we dont abort just because the va space is fragmented

* hex-mm: replaced more scalar divs with fastdiv and minor cleanup

* hex-mm: tighten up supported fusion checks to exactly match supported kernels

</details>

**Website:**
- <https://llama.app>

**Attestations:**
- <https://github.com/ggml-org/llama.cpp/attestations/44653803>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-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/b10758/llama-b10758-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-rocm-7.14-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-openvino-2026.3.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10758/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10758/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows arm64 (CUDA 13) (preview)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10758/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-openvino-2026.3.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10758/llama-b10758-bin-win-rocm-7.14-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/b10758/llama-b10758-ui.tar.gz)