github llama.cpp · 2d ago · inference

llama.cpp b10688 adds fa-vec tunings for M2

from English

The llama.cpp project has released build b10688, which includes a pull request adding fast vector (fa-vec) tunings for the M2 architecture.

This update provides binaries and frameworks across multiple platforms and hardware configurations. macOS builds are available for Apple Silicon and Intel, while iOS users can access an XCFramework. Linux support covers CPU, Vulkan, ROCm 7.14, OpenVINO, and SYCL variants for x64, arm64, and s390x architectures. Windows releases include CPU, OpenCL Adreno, Vulkan, ROCm 7.14, OpenVINO, SYCL, and CUDA 12/13 support for both x64 and arm64. Android arm64 binaries are also provided.

The release enables users to run llama.cpp on a wide range of devices and accelerators using the latest build artifacts.

Importance 1/3 Trust 1/3 llama.cpp Inference efficiency Local inference

Read original

github llama.cpp · just now · 1 view Live

llama.cpp b10721 fixes WebGPU crash and adds Windows CUDA 13.4 support

The llama.cpp project has released build b10721, which includes a critical fix for the WebGPU backend and expands hardware support on Windows.

github llama.cpp · 2h ago

llama.cpp b10718 extends MOE fusion to specdec and multi-token

The llama.cpp project released version b10718, which includes a significant update to its CUDA backend. The most notable change is the extension of Mixture of Experts (MOE) fusion to support speculative decoding (specdec), addressing previous limitations where MOE glu fusion and topk-router fusion were restricted to processing only one token at a time.

github llama.cpp · 5h ago · 1 view

llama.cpp b10721 fixes WebGPU crash and adds Windows CUDA 13.4 support

llama.cpp b10718 extends MOE fusion to specdec and multi-token

llama.cpp b10715 fuses DFlash encoder into KV cache injection

llama.cpp b10714 tunes Vulkan mat-vec rows for Strix Halo

llama.cpp b10706 adds SWIGLU_CLAMP and Vulkan shader support