github llama.cpp · 2d ago · inference

llama.cpp b11018 fixes SYCL memory allocation error on Arc B70

from English

The llama.cpp project released build b11018, which includes a fix for a memory allocation error occurring when using the Intel Arc B70 GPU with SYCL backend.

Resolves an issue where memory allocation failed for workloads exceeding 19.3GB on the Arc B70.
Provides binaries for macOS (Apple Silicon and Intel), Linux (CPU, CUDA, ROCm, OpenVINO, SYCL), Windows (CPU, CUDA, Vulkan, OpenCL, SYCL, ROCm, OpenVINO), Android, and UI.
Includes specific builds for Ubuntu x64/arm64/s390x with various accelerator support including CUDA 12/13, ROCm 10.0, and OpenVINO 2026.3.1.

This update ensures stable operation on Intel Arc B70 hardware by correcting the memory handling logic in the SYCL implementation.

Importance 1/3 Trust 1/3 llama.cpp Hugging Face Inference efficiency

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 · 1h ago · 1 view Live

llama.cpp b11044 updates hexagon im2col and releases binaries

The llama.cpp project has released version b11044, which includes an update to the hexagon backend for improved image-to-column (im2col) operations. The release provides pre-built binaries for macOS, Linux, Windows, Android, and openEuler across CPU, GPU, and other hardware accelerators.

github llama.cpp · 2h ago · 1 view

llama.cpp b11046 adds OpenCL support for flash_attn_f32_f16_bin kernel

llama.cpp b11044 updates hexagon im2col and releases binaries

llama.cpp b11045 adds ROLL op support to Hexagon backend

llama.cpp b11035 adds IQ3_S MMQ matmul kernels for Vulkan

llama.cpp b11026 skips gate_up_exps for Qwen35MoE