github llama.cpp · 1d ago · inference

llama.cpp b11097 adds A8 Q4_0 non-MoE dp4a binary kernel

from English

The llama.cpp project has released version b11097, which introduces an OpenCL binary kernel for the A8 Q4_0 non-MoE dp4a format.

The update adds support for the specific A8 Q4_0 quantization format via a new dp4a kernel.
Binaries are provided for macOS (Apple Silicon and Intel), Linux (CPU, Vulkan, CUDA 12/13, ROCm 10.0, OpenVINO, SYCL), Windows (CPU, Vulkan, CUDA 12/13, ROCm 10.0, OpenVINO, SYCL), Android, and openEuler.
An iOS XCFramework and a standalone UI build are also included in the release assets.

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

Read original

github llama.cpp · just now · 1 view Live

llama.cpp b11122 extends MMVQ GLU fusion and adds new SYCL fusions

The llama.cpp project has released version b11122, which includes significant updates to the SYCL backend. The release extends the MMVQ GLU fusion to support mixed quantization types and introduces new fusions for rms_norm+scale and ssm_conv+silu operations.

github llama.cpp · 14h ago · 11 views

llama.cpp b11111 adds Intel Xe flash attention optimization kernels

The llama.cpp project released build b11111, which introduces Vulkan-based Intel Xe flash attention optimization kernels for split k paths on Xe-LPG Plus, Xe2, and Xe3 architectures.

github llama.cpp · 17h ago · 9 views

llama.cpp adds DFlash support for HunyuanOCR and fixes draft conversion

The llama.cpp project has added support for DFlash speculative decoding with the HunyuanOCR model by exposing layer input tensors in the target graph. This change allows the draft model to read residual streams, enabling image requests to run successfully with a draft acceptance rate of approximately 0.5 and byte-identical OCR output compared to non-speculative runs.

github llama.cpp · 20h ago · 11 views

llama.cpp b11101 release allows repeated find_package calls for llama

The llama.cpp project has released version b11101, which includes a build system fix allowing repeated find_package calls for the llama library.

lab Hugging Face Blog · 21h ago · 10 views

Transformers adds GGUF support via ggml kernels for local inference

Hugging Face's Transformers library now supports loading GGUF quantized models, leveraging the underlying ggml kernels to bring performance close to llama.cpp. This integration allows developers to run quantized checkpoints directly within the standard PyTorch-based API on supported hardware.