b10322

ggml-org/llama.cppb10322Aug 7, 2026by github-actions[bot]
AI Summary

Optimizes the SYCL backend performance for SSM (State Space Model) convolution operations by coalescing window loads.
Key Highlights

Significant performance improvements on Arc Pro B70 hardware, achieving up to 1.85x speedup for SSM_CONV operations.
Optimized memory access patterns for interleaved A/B tensor layouts.
Benchmark results show consistent throughput gains on Qwen35 27B models.
Full Release Notes

<details open>

sycl: coalesce the ssm_conv window loads (#26612)

test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against
master, 6 reps, us/run:

  ne_a=[515,3328,1,1] ne_b=[4,3328,1,1]   n_t=512     97.68 -> 52.95   1.85x
  ne_a=[937,8192,1,1] ne_b=[4,8192,1,1]   n_t=934    516.16 -> 276.13  1.87x
  ne_a=[4,3328,1,1]   ne_b=[4,3328,1,1]   n_t=1        2.73 -> 2.71    flat

llama-bench on qwen35 27B Q4_K - Medium (48 of its 64 blocks run ssm_conv),
-ngl 99 -fa 1 -ctk f16 -ctv f16, interleaved passes of r=3:

  -b 2048 -ub 2048  pp2048  1045.1 / 1043.5 / 1043.7 -> 1069.5 / 1066.3 / 1065.9  +2.2%
  -b 2048 -ub 512   pp2048   771.8 /  772.7          ->  785.5 /  786.6           +1.8%
  -b 2048 -ub 512   tg128     23.81 /  23.88         ->   23.87 /  23.86          flat

</details>

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

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-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/b10322/llama-b10322-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-openvino-2026.2.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10322/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10322/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-openvino-2026.2.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b10322/llama-b10322-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/b10322/llama-b10322-ui.tar.gz)