ggerganov/llama.cpp b9279: 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.