github llama.cpp · 2d ago · inference

llama.cpp b11020 adds message delimiters to DeepSeek V3.2/V4 parser

from English

The llama.cpp project has released version b11020, which includes a functional update to the chat parsing logic. The primary change is the addition of message delimiters specifically for the DeepSeek V3.2 and V4 model parsers.

Added message delimiters to the DeepSeek V3.2/V4 parser in pull #29008.
Released binaries for macOS (Apple Silicon and Intel), iOS, Linux (CPU, Vulkan, CUDA, ROCm, OpenVINO, SYCL), Windows (CPU, OpenCL, CUDA, Vulkan, OpenVINO, SYCL, ROCm), Android, and openEuler.

This update ensures correct parsing of conversation structures for DeepSeek models within the llama.cpp framework.

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