github llama.cpp · just now · inference

llama.cpp b10665 adds DSpark support for Nemotron3.5

from English

The llama.cpp project released build b10665, which introduces DSpark support for the Nemotron3.5 model.

Adds DSpark support for Nemotron3.5 via updates to src/models/dflash.cpp.
Provides binaries for macOS (Apple Silicon and Intel), Linux (Ubuntu with CPU, Vulkan, ROCm, OpenVINO, SYCL), Android, Windows (CPU, CUDA 12/13, Vulkan, OpenCL, OpenVINO, SYCL, ROCm), and openEuler.

This release enables users to run Nemotron3.5 models using the DSpark format across a wide range of hardware architectures and operating systems.

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

Read original

github llama.cpp · 3h ago · 2 views

llama.cpp adds Qwen3.8-Flash-Next (qwen4exp) architecture support

The llama.cpp project has added support for the Qwen3.8-Flash-Next (qwen4exp) model architecture, implementing its specific components including hyper-connections, gated delta nets, Mixture of Experts, and PLE n-gram hash embeddings.

github llama.cpp · 10h ago · 4 views

llama.cpp b10653 adds TENSOR_READ_LAZY for model loading

The llama.cpp project has released build b10653, introducing the TENSOR_READ_LAZY feature to its model loader. This change includes the addition of the TENSOR_GET_ROW_LAZY function and a corresponding --tensor-read-lazy command-line flag.

github llama.cpp · 10h ago · 3 views

llama.cpp b10655 adds LIGHTNING_INDEXER support for Deepseek V4 ops on Vulkan

The llama.cpp project released build b10655, which introduces support for the LIGHTNING_INDEXER operation within the Vulkan backend to enable Deepseek V4 operations.

github llama.cpp · 1d ago · 6 views

llama.cpp b10639 fixes Vulkan warptile warp size assumption

The llama.cpp project released build b10639, which includes a fix for the Vulkan backend where warptiles previously assumed warp sizes were less than or equal to 64. This change clamps the warp size to work around issues with larger warps.

media Hugging Face Forums · 2d ago · 4 views

EdgeFirst publishes Rust pipeline validating YOLO models on 20 edge platforms

EdgeFirst has published the EdgeFirst Model Zoo on Hugging Face, featuring YOLOv5, YOLOv8, YOLO11, and YOLO26 models validated across 20 distinct edge platforms. The validation relies on a single Rust pipeline that handles zero-copy DMA pre-processing, model decoding, and post-processing directly on the target hardware.