Starstruk Logo MarkStarstruk

b10306

ggml-org/llama.cppb10306Aug 7, 2026by github-actions[bot]

AI Summary

A performance-focused release for SYCL backends, specifically optimizing the GLU (Gated Linear Unit) operations. It introduces a flat path for contiguous memory and refactors kernel launches for better performance on Arc Pro B70.

Key Highlights

  • Added contiguous fast path for fused GLU/SiLU operations in SYCL (#26354)
  • Consolidated fused-GLU kernels to reduce code duplication
  • Performance improvements: +14% f16 and +4% f32 for split operands on Arc Pro B70
  • Added performance test cases for SWIGLU

Full Release Notes

<details open>

sycl: *glu flat path (#26354)

* tests: add SWIGLU perf cases

perf mode had no GLU coverage. Adds SWIGLU at 17408 columns, 512 and
2048 tokens, f16 and f32, with the operands both fused and split.

* sycl: consolidate fused-GLU kernels

They differed only in which op_* they called, so take the op as an argument and share a common launcher.
Their block sizes were all 256, so launch geometry is unchanged;
SYCL_GELU_BLOCK_SIZE and SYCL_SILU_BLOCK_SIZE lose their last users so are dropped.

* sycl: contiguous fast path for the fused GLU ops

o0 == n and o1 == n collapse the de-interleave index math to the
identity, so dispatch a flat kernel in that case. It fires for
ggml_glu_split with packed operands; a fused [gate|up] tensor keeps the
strided path. test-backend-ops perf -o SWIGLU on an Arc Pro B70: split
+14% f16 and +4% f32, fused unchanged.

</details>

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

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-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/b10306/llama-b10306-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10306/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10306/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10306/llama-b10306-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/b10306/llama-b10306-ui.tar.gz)