github llama.cpp · 1h ago · inference

llama.cpp b11120 hides Vulkan internal symbols to fix state destruction

from English

The llama.cpp project released version b11120, which addresses a critical bug in the Vulkan backend by hiding internal symbols. This change prevents duplicate-dlopen state destruction issues that occurred when internal symbols were exported.

Fixes issue #29138 where interposed destructors destroyed the live vk_instance, causing device queries to hit GGML_ASSERT on vk_instance.device_indices.
Exports only GGML_BACKEND_API with hidden visibility, reverting the export behavior introduced in PR #28732.
Provides binaries for macOS (Apple Silicon and Intel), Linux (CPU, Vulkan, CUDA 12/13, ROCm 10.0, OpenVINO, SYCL, Snapdragon), Windows (CPU, OpenCL, CUDA 12/13, Vulkan, OpenVINO, SYCL, ROCm 10.0), Android, and openEuler.
Includes iOS XCFramework and UI builds alongside the various platform-specific binaries.

This update ensures stability for users relying on the Vulkan backend by resolving crashes caused by symbol interposition during library loading.

Importance 1/3 Trust 1/3 llama.cpp Inference efficiency Local inference

Read original

github llama.cpp · 6h ago · 13 views

llama.cpp b11118 introduces direct-mapped DMA cache for HVX FA mask handling

The llama.cpp project has released build b11118, which includes a new hex-dma feature introducing a direct-mapped DMA cache better suited for Hexagon Vector eXtended (HVX) FA mask handling.

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 · 17h ago · 13 views

llama.cpp b11104 adds support for binding llama-server to multiple addresses

The llama.cpp project released version b11104, introducing a new feature that allows the llama-server component to bind to multiple network addresses simultaneously.

github llama.cpp · 19h ago · 15 views

llama.cpp b11102 adds MiMo-V2.6 support

The llama.cpp project released build b11102, which introduces support for converting MiMo-V2.6 models.

lab Hugging Face Blog · 20h 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.