AI Briefing#llama-cpp
The latest AI and developer news about #llama-cpp, with the original source and a short summary.
The latest AI and developer news about #llama-cpp, with the original source and a short summary.
Harbor v0.4.19 has been released, supporting agent execution based on local inference backends and automatic injection of web search tools.
A bug in llama.cpp causes the KV cache of the Qwen3.6-35B-A3B model to be dropped, significantly degrading inference speed.
The llama.cpp server now supports native tool-calling capabilities, including file manipulation and shell command execution.
llama.cpp now supports NVIDIA FP4 quantization and Multi-Token Prediction (MTP) features.
Llama.cpp has added PDL support for Blackwell GPUs, improving token generation speed by 4-10%
The VRAM leak issue that occurred when using MTP models in the latest llama.cpp build has been resolved.
LM Studio added support for MTP speculative decoding in 0.4.14 Beta.
Bug fixes related to MTP and speculative decoding improvements have been merged into llama.cpp.
MTP speculative decoding has been added to llama.cpp, making Qwen3.6 27B up to 2.44x faster.
llama.cpp b9200 includes an optimization that improves MTP prompt processing speed.
An update has been released for llama.cpp that optimizes prompt decoding performance when using MTP.
The llama.cpp b9180 release adds MTP support and partial rollback.
MTP (Multi-Token Prediction) support has been officially merged into the llama.cpp project.
llama.cpp added MTP support, and Qwen3.6 MTP GGUF models were released.
Ollama has switched from a GGML-based build to direct llama.cpp support.
Hugging Face has released ml-intern, a tool for agents that controls ML libraries using local models.
TextGen has switched to an installation-free desktop app for Windows, Linux, and macOS.
Hermes Agent was introduced as a self-improving local AI agent for NVIDIA RTX PCs and DGX Spark.
llama.cpp's server and webui now support the continue generation feature for reasoning models.
llama-eval, a feature for measuring model performance in local environments, has been added to llama.cpp.
MiniCPM has released MiniCPM-V 4.6, unveiling a 1.3B vision-language model for mobile use.
llama.cpp is undergoing updates to resolve conflicts between MTP and multimodal features and support their integration.
The llama.cpp b9095 update enables tensor parallel processing on Blackwell PCIe GPUs without NCCL.
BeeLlama.cpp, a new fork that maximizes the performance of llama.cpp, has been released.