GGML
PulseAugur coverage of GGML — every cluster mentioning GGML across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Hugging Face integrates GGML and llama.cpp for local AI development
Hugging Face has announced the integration of GGML and llama.cpp, two key projects for running large language models locally on consumer hardware. This move aims to ensure the long-term development and accessibility of …
-
Microsoft releases VibeVoice-ASR-BitNet for real-time CPU inference
Microsoft has released VibeVoice-ASR-BitNet, a highly compressed automatic speech recognition model designed for real-time inference on edge CPUs without requiring a GPU. This model achieves significant speedups over ex…
-
audio.cpp 0.4 adds TTS/ASR models, full GGUF support
The audio.cpp project has released version 0.4, introducing support for several new high-quality text-to-speech (TTS) and automatic speech recognition (ASR) models, including Higgs Audio v3 TTS 4B and Fish Audio S2 Pro.…
-
Transcribe.cpp: New GGML-based open-source speech-to-text library released
Transcribe.cpp is a new open-source speech-to-text library built on GGML. It supports a wide array of models, offering numerical validation and WER testing for accuracy. The library provides cross-platform GPU accelerat…
-
Hugging Face integrates GGML and llama.cpp to advance local AI
Hugging Face has announced that GGML and llama.cpp are joining their platform. This integration is expected to bolster the long-term development of local AI capabilities. The move signifies a commitment to supporting op…
-
TurboQuant AI compression sees community adoption, but hype cools
Four months after its announcement, Google's TurboQuant algorithm for compressing AI model KV caches has seen significant community adoption but with a more nuanced understanding of its capabilities. While Google has no…
-
Open-source AI pipeline generates game assets locally
A developer has created a comprehensive pipeline for generating game assets using open-source AI models, ported to GGML for local execution. The pipeline includes tools for text-to-speech with voice cloning (OpenMOSS), …
-
TensorSharp adds Vulkan backend for LLM inference, benchmarks against llama.cpp
TensorSharp, an open-source LLM inference engine, has released an initial version of its GGML Vulkan backend, aiming to improve performance on GPUs. The update was tested successfully on Nvidia and Intel GPUs, with the …
-
audio.cpp adds music, SFX, and long-form TTS models via C++/GGML
The audio.cpp project has released significant updates, introducing native C++/GGML support for several new audio models including ACE-Step, Stable Audio, HeartMuLa, RoFormer, and HTDemucs. This expansion enables music …
-
GGML and llama.cpp join Hugging Face to bolster local AI development
Hugging Face has announced that GGML and llama.cpp are joining their platform. This integration aims to ensure the long-term development and accessibility of local AI models. The move is expected to benefit the communit…
-
Portable AI agents can now run from a 340MB USB stick package
A new project called norax-portable enables the creation of self-contained AI agents that can run on any x86_64 Linux machine from a USB stick. The package, which is only 340MB, includes Python, Ollama (CPU-only), and m…
-
audio.cpp framework offers faster audio model inference
A new C++ inference framework called audio.cpp has been developed, built on top of ggml, to run various audio models including TTS, ASR, and voice conversion. The framework aims to consolidate multiple audio models into…
-
Hugging Face integrates GGML and llama.cpp for local AI development
Hugging Face has announced that GGML and llama.cpp are joining their platform. This integration is expected to ensure the long-term development of local AI capabilities. The move signifies a commitment to supporting ope…
-
NVIDIA Parakeet speech-to-text ported to ggml for faster CPU/GPU use
A developer has successfully ported NVIDIA's Parakeet speech-to-text models to the ggml framework, enabling them to run efficiently on CPUs and GPUs without Python or PyTorch. This port achieves byte-for-byte identical …
-
Developer runs LLMs on $50 AMD RX 580 GPU using Vulkan
A developer demonstrated running large language models and image generation software on an older AMD RX 580 GPU with 8GB of VRAM, a feat previously thought impossible for such hardware. By leveraging the Vulkan backend …
-
Google's Gemma 4 adds MTP for faster local inference, VibeVoice ported to C++, Ollama gets desktop layer
Google has released Gemma 4 with Multi-Token Prediction (MTP), a feature that allows the model to predict multiple tokens simultaneously, significantly speeding up local inference. Additionally, a C++ port of Microsoft'…
-
Ollama v0.6.8 and OpenClaw 2026.5.3 release with speedups and fixes
Ollama has released version 0.6.8, introducing performance enhancements for the Qwen 3 MoE model on both NVIDIA and AMD hardware. This update also addresses several issues, including problems with GGML assertions, image…
-
Hugging Face integrates GGML and llama.cpp for local AI
Hugging Face has announced that GGML and llama.cpp are joining the platform. This integration aims to foster the continued development and long-term progress of local AI initiatives. The move is expected to benefit the …
-
George Hotz's tiny corp unveils $15K AI computer and RISC-based tinygrad framework
George Hotz's company, tiny corp, has launched the tinybox, a $15,000 personal AI computer designed for local model training and inference. The tinybox boasts 738 FP16 TFLOPS and 144 GB of GPU RAM, capable of running a …