NVIDIA Dynamo Details EPD Disaggregation for Multimodal
Learn how NVIDIA Dynamo uses Encode-Prefill-Decode (EPD) disaggregation to accelerate multimodal model serving, reduc ...
Goodfire Traces Olmo Behavior with Ai2 Post-Training Stack
Goodfire uses Ai2’s open post-training stack to trace and predict unwanted behaviors in Olmo models, showcasing ...
Nex-AGI Releases Agent Model Nex-N2.5-Pro
Nex-AGI announces the Nex-N2.5 agent model family. Weights for mini, Pro, and Max are available on Hugging Face, with ...
Nex-AGI Releases Open-Weight Long-Task Model Nex-N2.5-mini
Discover the specs, performance, and hardware requirements for Nex-N2.5-mini, an open-weight multimodal model by Nex- ...
Mistral AI Raises €3B in Series D to Accelerate Open-Weight AI
Mistral AI secures €3 billion in Series D funding to expand frontier research and continue open-weight model developm ...
OpenBMB Releases MiniCPM5-2B-GGUF for On-Device AI
Discover OpenBMB’s MiniCPM5-2B-GGUF, a 2B-class open-weight model for on-device use. Learn specs, benchmarks, h ...
OpenBMB Releases MiniCPM5-2B: A SOTA 2B On-Device Model
OpenBMB has released MiniCPM5-2B, a 2B-class on-device model delivering SOTA performance in coding, math, long contex ...
Inference Engine Updates and Practical GGUF Models Like Qwopus
Explore the latest local AI trends, including inference engine updates like ggml v0.23.0 and ExLlamaV3, and GGUF rele ...