github llama.cpp · 1h ago · inference

llama.cpp b10663 fixes RMS_NORM_MUL weight-offset bugs

from English

The llama.cpp project has released version b10663, which includes a fix for RMS_NORM_MUL weight-offset bugs affecting grouped and broadcast norms.

Fixes RMS_NORM_MUL weight-offset bugs for grouped/broadcast norms (PR #27798).
Provides binaries for macOS (Apple Silicon and Intel), iOS, Linux (CPU, Vulkan, ROCm 7.14, OpenVINO, SYCL), Android, Windows (CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, ROCm 7.14), and openEuler.

This release ensures correct normalization behavior for specific model architectures while providing updated binaries across supported platforms.

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

Read original

github llama.cpp · just now Live

llama.cpp b10665 adds DSpark support for Nemotron3.5

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

github llama.cpp · 2h ago · 1 view

llama.cpp b10662 adds ctx-per-slot for unified KV cache

The llama.cpp project released build b10662, introducing a new `--kv-unified-per-slot` argument that allows users to specify context per slot for the unified KV cache. This change replaces the previous context fraction mechanism with context pool slots and refactors the underlying implementation.

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 · 4h ago · 1 view

llama.cpp b10658 adds DFlash2 support and fixes mrope bug

The llama.cpp project released build b10658, introducing support for the DFlash2 specification which includes local convolution and a candidate selector. This update also addresses a specific mrope bug within the codebase.

github llama.cpp · 4h ago · 1 view

llama.cpp bundles HIP runtime DLLs with Windows ROCm release

The llama.cpp project has updated its Windows ROCm release to bundle the necessary HIP runtime DLLs directly alongside the binaries. This change addresses issue #26929 by ensuring the correct HIP runtime loads instead of potentially conflicting with the driver's copy in System32.