github llama.cpp · just now · inference

llama.cpp b11132 adds Gemma 4 DSpark draft backbone support

from English

The llama.cpp project released version b11132, introducing support for the Gemma 4 DSpark draft backbone. This update enables GGUF conversion and runtime capabilities for full-attention and SWA Gemma 4 drafts, including tied output weights and boolean backbone metadata.

Added dspark support for Gemma 4 draft models with full-attention and SWA variants.
Implemented inference of Gemma draft features from metadata via the dflash mechanism.
Released binaries for macOS (Apple Silicon and Intel), Linux (CPU, Vulkan, CUDA, ROCm, OpenVINO, SYCL, Snapdragon), Windows (CPU, OpenCL, CUDA, Vulkan, OpenVINO, SYCL, ROCm), Android, and iOS.

This release allows users to utilize Gemma 4 models within the llama.cpp ecosystem on a wide range of hardware platforms.

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

Read original

github llama.cpp · 5h ago · 12 views

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 · 19h ago · 13 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 · 22h 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 · 1d ago · 12 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 · 1d ago · 13 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.