b10520

ggml-org/llama.cppb10520Aug 20, 2026by github-actions[bot]

AI Summary

Fixes a compilation issue on 32-bit ARM architectures by gating the use of `__fp16` on the IEEE half format, ensuring compatibility with toolchains that provide the type but use a different format.

Key Highlights

  • Fixed compilation on 32-bit ARM with NEON
  • Gated __fp16 usage on IEEE format
  • Fixed NEON+FMA block compatibility

New Features

  • ARM FP16 format compatibility fix

Full Release Notes

<details open>

ggml-cpu: gate __fp16 on __ARM_FP16_FORMAT_IEEE (#26860)

* ggml-cpu: gate __fp16 on __ARM_FP16_FORMAT_IEEE

__ARM_NEON only signals NEON availability. The __fp16 type also needs
the IEEE half format, implied on AArch64 but selected with
-mfp16-format=ieee on 32 bit Arm, where the compiler otherwise rejects
the type.

The guard keeps every toolchain that provides the type on the same code
and sends that one configuration to the generic lookup path.

* ggml-cpu: gate the NEON+FMA block on __ARM_FP16_FORMAT_IEEE

Both halves of the F16 section dereference __fp16, so armv7 with
neon-vfpv4 hits the same unknown type error. Without the IEEE
format the configuration now falls back to the scalar path.

Address review from @JonathanC-ARM

</details>

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

**Attestations:**
- <https://github.com/ggml-org/llama.cpp/attestations/41979350>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-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/b10520/llama-b10520-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-vulkan-arm64.tar.gz)
- Ubuntu x64 (ROCm 7.14)[DISABLED](https://github.com/ggml-org/llama.cpp/pull/26969)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-openvino-2026.3-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10520/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10520/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows arm64 (CUDA 13) (preview)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10520/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-openvino-2026.3-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10520/llama-b10520-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/b10520/llama-b10520-ui.tar.gz)