# ggerganov/llama.cpp b9279: b9279 — retained record

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

Canonical: https://highsignal.app/data/records/8ad6ac37629e2b01

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


source: [github](https://highsignal.app/data/github) (github:ggerganov/llama.cpp)  published 2026-05-22 01:51 ingested 2026-05-22 09:02

[Apple Inc.](https://highsignal.app/entities/AAPL)[original source ↗](https://github.com/ggml-org/llama.cpp/releases/tag/b9279)

## extract

<details open>

vulkan: fuse snake activation (mul, sin, sqr, mul, add) (#22855)

* vulkan: fuse snake activation (mul, sin, sqr, mul, add)

Add snake.comp shader with F32 / F16 / BF16 pipelines and
ggml_vk_snake_dispatch_fused. The matcher recognizes the naive 5 op
decomposition emitted by audio decoders (BigVGAN, Vocos) for snake
activation y = x + sin(a*x)^2 * inv_b and rewrites it to a single
elementwise kernel.

test_snake_fuse from the CUDA PR now also compares CPU naive vs
Vulkan fused across F32 / F16 / BF16.

* vulkan: address jeffbolznv review for fused snake activation

Rename T / C to ne0 / ne1 in the shader and push constants to match
the standard naming convention used across the Vulkan backend.

Tighten ggml_vk_can_fuse_snake: require x and dst to be contiguous
(the shader uses idx = i0 + i1 * ne0) and require a / inv_b to be
tightly packed on the broadcast dim (the shader reads data_a[i1]).

* vulkan: tighten snake fusion type checks for all operands (address jeffbolznv review)

* vulkan: reject snake fusion when ne[2] or ne[3] > 1 (address jeffbolznv review)

* vulkan: address 0cc4m review for fused snake activation

snake.comp is renamed to follow the ggml DATA_A_* / A_TYPE convention.
A_TYPE now applies to the activation tensor data_a instead of the
broadcast multiplier, and the bindings become data_a (A_TYPE), data_b
(float), data_c (float) and data_d (D_TYPE). A header at the top of
the shader maps each buffer to its role in y = x + sin(b * x)^2 * c.

On the C++ side, ggml_vk_can_fuse_snake reuses the existing snake_pattern
constant instead of duplicating the op list, sin_node is extracted as a
named local alongside the other chain nodes, and the broadcast operands
a and inv_b are now required to be GGML_TYPE_F32 to match the hardcoded
float bindings on data_b and data_c (the previous a->type == x->type
would silently reject any future BF16 or F16 chain once the supports_op
gate for SIN / SQR is lifted). ggml_vk_snake_dispatch_fused gets an
explicit GGML_TYPE_F32 case and GGML_ABORT on default in place of the
silent f32 fallback, and a stale comment about data_a[i1] / data_inv_b[i1]
is refreshed to match the new binding names.

</details>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-macos-arm64.tar.gz)
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-macos-arm64-kleidiai.tar.gz)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-openvino-2026.0-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-cpu-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9279/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-cuda-13.1-x64.zip) - [CUDA 13.1 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9279/cudart-llama-bin-win-cuda-13.1-x64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-vulkan-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-sycl-x64.zip)
- [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-win-hip-radeon-x64.zip)

**openEuler:**
- [openEuler x86 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-310p-openEuler-x86.tar.gz)
- [openEuler x86 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-910b-openEuler-x86-aclgraph.tar.gz)
- [openEuler aarch64 (310p)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-310p-openEuler-aarch64.tar.gz)
- [openEuler aarch64 (910b, ACL Graph)](https://github.com/ggml-org/llama.cpp/releases/download/b9279/llama-b9279-bin-910b-openEuler-aarch64-aclgraph.tar.gz)

## retained text

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