# ggerganov/llama.cpp b9275: b9275 — retained record

> Retained github record from github:ggerganov/llama.cpp.

Canonical: https://highsignal.app/data/records/88a3d4799a57f18b

[← sources](https://highsignal.app/data)


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-05-21 22:59 ingested 2026-05-22 09:02

[Apple Inc.](https://highsignal.app/entities/AAPL)[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b9275)

## extract

<details open>

metal : optimize concat kernel and fix set kernel threads (#23411)

* metal : fix GGML_OP_SET kernel threads

* tests : extend test_cpy to support different src/dst shapes

Extend test_cpy to support different source and destination tensor shapes
for CPY operations (reshaping), where the total number of elements must match.

- Renamed ne -> ne_src, added ne_dst parameter (default: use src shape)
- Added 50 new reshaping test cases covering 1D<->2D<->3D<->4D conversions
- Tests exercise 1024 boundary, small shapes, and large dimensionality changes
- Fixed dangling reference bug (storing & to temporary std::array)
- Updated all existing test calls with permute/transpose args for compatibility

Assisted-by: llama.cpp:local pi

* metal : optimize concat kernel with row batching for small widths

When ne0 < 256, batch multiple rows into a single threadgroup to improve
occupancy. This avoids underutilizing the GPU when processing narrow tensors.

- Dispatch nth = min(256, ne0) threads per group
- Calculate nrptg (rows per threadgroup) to fill up to 256 threads
- Update kernel index calculation to handle the row batching
- Add boundary check for i1 >= ne1

Assisted-by: llama.cpp:local pi

* tests : clean-up

* tests : refactor CPY shape tests to use dimension permutations

Replace 75 hardcoded test cases with a loop over permutations of
{3, 5, 7, 32} (total elements: 3360). Each src permutation is tested
against canonical sorted and reverse dst, skipping identical shapes.
Covers F32, F16, and Q4_0 (when both src and dst ne0 == 32).

Assisted-by: llama.cpp:local pi

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-macos-arm64.tar.gz)
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-macos-arm64-kleidiai.tar.gz)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-openvino-2026.0-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9275/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9275/cudart-llama-bin-win-cuda-13.1-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-vulkan-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-win-hip-radeon-x64.zip)

**openEuler:**
- [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-310p-openEuler-x86.tar.gz)
- [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-910b-openEuler-x86-aclgraph.tar.gz)
- [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-310p-openEuler-aarch64.tar.gz)
- [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9275/llama-b9275-bin-910b-openEuler-aarch64-aclgraph.tar.gz)

## retained text

No document body was retained for this record — only its metadata was stored.
