NVIDIA has documented a threefold optimization approach to accelerate MoE inference, tested on the 124-billion-parameter Ling-3.0-flash model. By utilizing specialized Humming kernels, FP8 precision for the LM head, and Multi-Token Prediction, developers can achieve a 42.5% throughput increase and a 24.5% reduction in latency.
Google has updated its A2UI generative UI protocol to include swappable inference formats, addressing latency and reliability issues found in the previous Direct JSON approach. A new format, A2UI Express, reduces token usage by up to 3x and latency by up to 3x by using a concise Python-like syntax.
Google has launched Gemini Robotics Embodied Reasoning 2 (ER 2) in public preview on the Gemini platform. This model acts as a high-level cognitive layer for robotics, capable of planning, self-correcting tasks, and managing multi-robot systems via natural language instructions.
Researchers have introduced the Boa Compressor, an online tool utilizing a Mamba state-space model to compress long-form context into shorter representations in linear time. By distilling knowledge from full-context LLM interactions, this method allows for efficient per-query inference without the massive latency overhead of transformer-based compression.
Google has introduced Gemini Omni, a new video-generation model capable of creating and editing clips from text and image prompts. The model is now the default for Google's video workflows, while the previous Veo model has been deprecated in the API.
OpenAI has officially released GPT-6.1 Terra, a new model specifically engineered to excel in visual reasoning, precise computer navigation, and natural language generation.
Amazon Bedrock now supports explicit and implicit prompt caching for OpenAI models, allowing you to store and reuse static prompt prefixes like tools, instructions, and conversation history. By avoiding the re-processing of identical tokens across turns, you can significantly lower input costs and improve responsiveness in complex agent workflows.
IBM has updated its software ecosystem to treat the Spyre dataflow accelerator as a first-class PyTorch backend. By leveraging TorchDynamo and TorchInductor, developers can now run models on IBM Z, LinuxONE, and Power systems using standard PyTorch workflows and vLLM plugins.
Z.ai's GLM 5.3 Flash, a multimodal 320B-parameter Mixture-of-Experts model with 18B active parameters, is now available through Mistral's platform. It offers a 1M-token context window and is built for developer agent workflows, visual coding, and complex tool-use tasks. Pricing is set at $0.15 per million input tokens, $0.03 per million cached input tokens, and $0.50 per million output tokens.
Cohere launched Rerank 5, its newest enterprise reranking models, in Pro and Fast tiers. Rerank 5 Pro leads major public benchmarks including BRIGHT, ViDoRe V3, BEIR and nanoMTEB, while Rerank 5 Fast offers near-leading quality at lower cost and higher throughput. The release introduces Context Focus, which returns the most relevant text spans within documents rather than whole documents, and calibrated relevance scores that read as probabilities across models and domains.
NVIDIA has added three new open, commercially licensed components to its Nemotron Retriever lineup: Embed models (8B and 1B, in BF16 and NVFP4) for searching text and images, a Rerank model (8B) that reorders retrieved evidence by relevance, and a compact 631M Parse model that converts document images into structured text. The goal is to feed AI agents with better, more relevant evidence so they need fewer search rounds and fewer inference tokens to answer a question. NVIDIA reports the new Embed and Rerank models top the ViDoRe v3.1 leaderboards for dense retrieval and reranking respectively.
AI research company i14 partnered with AWS to port its Laplace 3B model, a 24-layer architecture built on Gated Linear Attention (GLA) instead of standard transformer attention, onto AWS Trainium2 using native PyTorch (TorchNeuron Native). Rather than a KV cache that expands with every token, the model keeps a constant 29.5 MB recurrent state per sequence. On a single trn2.48xlarge instance, the team reached about 120,000 training tokens per second and served 11,544 output tokens per second across 1,280 simultaneous sequences through an unmodified vLLM engine.