Starstruk Logo MarkStarstruk

b9817

ggml-org/llama.cppb9817Jun 26, 2026by github-actions[bot]

AI Summary

Major update to the OpenVINO backend including version upgrade to 2026.2.1, removal of hardcoded compute types, and new operator support like GLU SwiGLU OAI.

Key Highlights

  • Update to OpenVINO 2026.2.1
  • Self-contained release packages
  • Removal of hardcoded compute op types
  • New softmax support with sink input
  • New GLU SwiGLU OAI operator

New Features

  • New OpenVINO operator: glu_swiglu_oai
  • Optimized mul_mat_id convert process for large sizes
  • Modified add_id to support 2D/4D tensors

Full Release Notes

<details open>

openvino: Update to OV 2026.2.1, self-contained release packages, operator improvements (#24974)

* Update to OV 2026.2.1, Make OV release packages self-contained

* Update to OV 2026.2.1, Make OV release packages self-contained

* OpenVINO Backend: Remove compute_op_type hardcoded sets (#222)

* OpenVINO Backend: Remove compute_op_type hardcoded sets

* revert get_op_type removal

* OpenVINO backend: enable softmax with sink input

* OpenVINO backend: opt mul_mat_id convert process for large size

* OpenVINO backend: Modify add_id to support 2D/4D

* OpenVINO Backend: Add glu_swiglu_oai

* PR review: fix paths

* PR review: fix path consistency

---------

Co-authored-by: Mostafa <mostafas.main.email@gmail.com>
Co-authored-by: Xuejun <Xuejun.Zhai@intel.com>

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-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/b9817/llama-b9817-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9817/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9817/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9817/llama-b9817-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/b9817/llama-b9817-ui.tar.gz)