github llama.cpp · 2d ago · inference

llama.cpp b11012 adds Vulkan support for qwen4exp hc ops

from English

The llama.cpp project has released version b11012, which introduces Vulkan support for qwen4exp hc operations via pull request #28988. This update also includes a fix for a stale comment.

The release provides binaries and frameworks across multiple platforms and hardware accelerators:

macOS: Apple Silicon (arm64), Intel (x64), and iOS XCFramework.
Linux: Ubuntu builds for CPU, Vulkan, CUDA 12/13, ROCm 10.0, OpenVINO, and SYCL.
Windows: Builds for CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and ROCm 10.0.
Android: arm64 CPU support.

This release enables users to run qwen4exp models with high-compute operations on Vulkan-compatible GPUs across supported operating systems.

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

Read original

github llama.cpp · just now · 1 view Live

llama.cpp b11046 adds OpenCL support for flash_attn_f32_f16_bin kernel

The llama.cpp project released version b11046, which introduces OpenCL support for the `flash_attn_f32_f16_bin` kernel. This update also includes guarded prefill functionality for Flash Attention on OpenCL devices.

github llama.cpp · 5h ago · 1 view

llama.cpp b11042 adds OpenCL A8 Q6_K binary kernel

The llama.cpp project has released version b11042, which introduces a new OpenCL binary kernel for A8 Q6_K non-MoE models. This update also includes fixes for layout compatibility within the OpenCL backend.

github llama.cpp · 9h ago · 1 view

llama.cpp b11039 adds SWA pattern support to model-saver and loaders

The llama.cpp project released build b11039, which updates the model-saver to write sliding window attention (SWA) patterns and MLA SWA geometry for all models using SWA. The change ensures that the `sliding_window_pattern` is written as a per-layer flag rather than being collapsed to a scalar, preserving exact data representation.

github llama.cpp · 1d ago · 6 views

llama.cpp b11024 updates OpenVINO to 2026.4 and fixes warnings

The llama.cpp project released build b11024, which primarily updates the OpenVINO integration to version 2026.4.

github llama.cpp · 1d ago · 2 views

llama.cpp b11025 extends Nemotron MTP support

The llama.cpp project has released build b11025, which includes an extension of Nemotron Multi-Token Prediction (MTP) support.