AWS released a push-based NIXL connector for vLLM that changes how key-value (KV) cache data moves between prefill and decode instances in disaggregated LLM serving. Instead of the decode instance pulling KV blocks after prefill finishes, the decode instance registers its target memory in advance and the prefill instance writes the KV data directly once ready, moving coordination work off the critical path. Benchmarked on a 1-prefill/1-decode Qwen3-32B deployment using EC2 P5en instances with EFA, push mode delivered up to 3x better time-to-first-token (TTFT) and up to 30% better time-per-output-token (TPOT) than the default pull mode, especially under high request rates.
Google Cloud published a reference architecture for building AI agents that coordinate long-running, GPU-heavy scientific tasks like protein folding and compound screening, which break standard single-LLM-agent setups due to timeouts and context overflow. The design separates a cognitive orchestrator (Gemini on Agent Runtime) from a GPU execution layer (NVIDIA NIMs like ESMFold and GenMol on GKE) and wraps both in an enterprise governance plane with agent identity, a gateway, a registry and Model Armor. It also lays out best practices such as passing bulky data by reference instead of inline, streaming progress updates, and gating irreversible actions behind human approval.
IBM has released Granite Switch 4.1 in 8B and 30B sizes, a modular system that runs chat, decision-making and speech transcription from one hosted endpoint instead of separate models. The update adds a general-purpose Decision adapter, a specialized Guardian adapter for safety-related classifications, and an embedded ASR model, Granite-Speech-5.0-Turbo-CTC, which tops the OpenASR Leaderboard. Despite bundling three capabilities, the combined model uses roughly the same VRAM as the base model alone.
Meta published Muse Spark Open, an open-weight mixture-of-experts model with about 816 billion total parameters and 42 billion active per token. It accepts text, images, audio and video as input and generates text, with a context window of up to 1 million tokens. Meta positions it as a coding-optimized, agentic model built on top of the smaller Muse Glimmer architecture, calling it the most capable US open-weights model released so far.
Swiss AI released Apertus 1.5, a continued pretraining of its open Apertus 1.0 models (8B and 70B, Apache 2.0) with native image and experimental audio understanding, a 4x larger context window of 262,144 tokens, an optional thinking mode, and improved instruction-following and tool use. The models were trained on a total of 19T (8B) and 17T (70B) tokens, with full training data, recipes and intermediate checkpoints published for reproducibility. The team also published detailed, standardized evaluation cards and announced early API access from providers like Swisscom and Infomaniak, plus a roadmap for a ~600B-parameter MoE Apertus 2.0.
Researchers describe a system called FlowSpec that converts a creditor's legal call procedure into machine-readable instructions, tool restrictions, training signals and test cases for a voice agent. A 9-billion-parameter model was trained on calls covering nearly 300 randomly generated procedures, then tested on four procedures it had never encountered, including one entirely held-out family of scripts, to see whether compliance behavior transfers.
GitHub replaced its LLM-based pipeline for detecting generic secrets (like passwords and API keys) with a fine-tuned ModernBERT classifier combined with regex candidate generation. The new two-stage system improved detection accuracy while cutting scan time and serving costs dramatically, and it's now fast enough to run during push protection, not just after code is committed.
Liquid AI has published LFM2.5-24B-A2B, a mixture-of-experts model with 24B total parameters but only 2B active per token, designed to run reasoning agents on local hardware. The release expands the context window to 131K tokens, doubles the vocabulary size, and was trained on roughly double the pretraining data of its predecessor. On agentic and tool-use benchmarks the model performs on par with or better than models that have about 50% more parameters, while delivering fast inference speeds on both consumer and data-center hardware.
Orca Security built Discovery AI, an Amazon Bedrock-based agent that turns plain-English security questions into structured queries against its Sonar system, which tracks over 900 cloud resource types. Rather than relying on one large model with the full schema stuffed into every prompt, the production version splits the work across nine specialized stages and multiple foundation models. The result: dramatically lower cost, faster responses, and better accuracy on complex queries, now running live since March 2026.
AWS detailed three kernel-level optimizations for Mixture-of-Experts (MoE) model serving on Hopper GPUs, implemented in collaboration with the vLLM community and shipped in Amazon SageMaker AI's LMI container. The changes target the inefficiencies of fused MoE computation during low-batch decode, which previously left Tensor Cores underutilized. Combined, the optimizations deliver up to 10% higher throughput and up to 9% faster time-to-first-token (TTFT).
NVIDIA has released the full Run:ai platform as open source, adding it as a foundation of the NVIDIA DSX AI Factory Platform for AI workload and GPU orchestration on Kubernetes. The release includes four modular components — KAI Scheduler, GPU Fractioning Operator, KAI Resource Management, and Workload Map — that can be adopted together or independently. Eight ecosystem partners, including Crusoe, Mirantis, Nebius, OpenNebula Systems, Rafay, Saturn Cloud, Spectro Cloud, and vCluster, are integrating the platform into their own offerings.
Amazon Web Services researchers published a method called 'priming' that converts pretrained Transformer models into hybrid architectures mixing attention and state space model (SSM) layers, reusing existing weights instead of retraining from scratch. The approach cuts pretraining costs by over 99% and lets a 32-billion-parameter hybrid model match its source Transformer's quality while decoding up to twice as fast. Amazon tested three SSM types and released an open-source model zoo, training code, and serving tools under Apache 2.0.
Mistral AI has released Voxtral Mini 4B Realtime Arabic, a streaming speech-to-text model fine-tuned for Arabic dialects, Modern Standard Arabic, and code-switching between languages. The 4.4-billion-parameter model processes 16 kHz audio in real time with a configurable transcription delay, achieving an 8.82% average Character Error Rate across seven Arabic benchmarks at a 480ms delay — close to the offline Voxtral Transcribe Arabic model's 7.91% CER. It was co-developed with Morocco's digital transition ministry as part of a sovereign AI partnership and is released under Apache 2.0.
Google released ML Drift, an open-source, cross-platform GPU compute engine for on-device ML inference, replacing the legacy TFLite GPU delegate. It unifies shader handling across OpenGL ES, OpenCL, Metal and WebGPU, adds 5D tensor support, and introduces stage-aware optimizations for LLM prefill/decode. It is already running in production in Chrome, YouTube Shorts, Google Photos, Meet and partner apps from Adobe and Snap.
Google has released the Developer Knowledge API, a structured, machine-readable source for Google Cloud, Firebase and Android documentation aimed at AI agents and developer tooling. Instead of scraping web pages or relying on an LLM's training cutoff, agents and CLIs can now query fresh, Markdown-formatted docs through several interfaces: a gcloud CLI surface, an installable agent skill, client libraries, and a browser-based API explorer. The underlying index is refreshed frequently so retrieved answers stay close to the latest published documentation.
AWS describes a new two-stage access control architecture for Retrieval Augmented Generation (RAG) in Amazon Quick and Amazon Bedrock Knowledge Bases. Instead of relying only on periodically synced access control lists (ACLs), the system now verifies permissions in real time against the authoritative data source (e.g. Google Drive, SharePoint, Confluence) at query time, before passing content to the LLM. AWS says this closes security gaps caused by stale or incorrectly mapped permissions between sync cycles. Mondelēz International, with over 35,000 employees, is cited as a customer using this approach.
AssemblyAI launched a hosted deployment of the open-source Qwen3.5 4B model on its LLM Gateway, optimized specifically for rewriting raw speech-to-text output into clean, formatted text. On voice rewrite tasks like dictation cleanup and transcript formatting, the model averaged 612ms response time—1.9x faster than GPT-4.1—at 94% lower cost per hour of audio processed. The model is priced at $0.10/$0.50 per million tokens (prompt/completion) and supports only max_tokens, temperature, and stream parameters, with no tool calling.
Google has launched EmbeddingGemma 2, a Gemma 4-based embedding model released under Apache 2.0 that places text, code, images, video and audio in one shared 768-dimensional vector space. It's modular, so developers load only the encoders they need: 270M parameters for text and code alone, scaling up to 740M for every modality. Google reports a 14% jump over EmbeddingGemma 1 on the MTEB Code benchmark while keeping the earlier model's multilingual text accuracy.
GitHub has published ReviewBench, a research-preview benchmark designed to compare AI code review agents on a common, auditable standard. The dataset draws on 219 real public pull requests across 19 languages and 187 repositories, chosen to mirror the language and size distribution found across 103.9 million GitHub pull requests. Ground truth comes from a blended pool of human reviewers, static analysis tools, and multiple frontier LLMs, cross-checked by senior engineers who agreed with the benchmark's labels 96.6% of the time. GitHub says it has already used ReviewBench internally to track its own Copilot code review (CCR) product, and that offline benchmark movement reliably predicted the direction of later production A/B tests.
GitHub Security Lab built an open-source 'Taskflow Agent' that uses custom AI prompt workflows to audit code for vulnerabilities, and used it to find and report over 24 vulnerabilities in Android applications. Two detailed examples show the agent finding a location-tracking flaw in the OsmAnd navigation app and an account-takeover chain in the Wikipedia Android app via a deeplink parsing bug. The team notes LLMs are strong at finding complex logic vulnerabilities and understand API behavior well, but struggle to correctly judge severity and often produce false positives, so findings still require human review. The taskflows are open source and can be run on any GitHub repository via a Copilot-powered codespace script, though running them consumes premium model requests and can take hours.
AWS released a step-by-step walkthrough showing how to give Claude Desktop (on Amazon Bedrock) live internet access through Amazon Bedrock AgentCore Gateway, closing the gap left by the model's training cutoff. The setup wires AWS IAM Identity Center SSO through Amazon Cognito as a SAML-to-OAuth federation layer, issuing JWTs that the AgentCore Gateway validates on every request. The Web Search capability itself is MCP-compatible and runs on an internal Amazon web index covering tens of billions of documents, so no query traffic leaves AWS and no third-party API key is needed. The feature is currently limited to three AWS Regions: us-east-1 (N. Virginia), eu-west-1 (Ireland), and ap-northeast-1 (Tokyo).
Google announced that its Antigravity SDK now supports running agentic workflows locally and offline, with initial support for Gemma 4 26B A4B running via Google AI Edge's LiteRT. Developers can build agents that run entirely on-device, without cloud API costs or internet dependency. Google also demonstrated a hybrid 'Architect-Builder' pattern where a cloud model (Gemini 3.8 Flash) plans tasks and a local swarm of Gemma 4 26B instances does the heavy execution, keeping source code off the cloud.