Skip to content
Thursday, 19 November 2026
Tenesys AI News
Subscribe

All News

TENESYS AI NEWS tracks the most important AI news and explains what changed, why it matters and whether a technology is worth testing.

“LLM” — 133 articles ✕

Models· Important

Google launches native PyTorch inference engines for vLLM and SGLang on TPU

Google announced new vLLM and SGLang inference engines built directly on PyTorch for TPU, developed with Inferact and RadixArk respectively. The engines run on a new TorchTPU layer that makes TPUs a native PyTorch device, replacing the previous JAX-based backend approach. Google reports a public benchmark result of 2.01 cents per million tokens in high-concurrency configurations via the SemiAnalysis InferenceX project, plus support for agentic workloads, long context, disaggregated serving and multimodal models.

Google Developers
Agents· Important· 🧪 Worth Testing

llm-d 1.0 released: open-source Kubernetes-native inference stack matures for production

Red Hat, IBM, and Google announced llm-d 1.0, a Kubernetes-native distributed inference serving system that moves beyond proof-of-concept performance tricks into full production readiness. The release adds multi-tenant quality of service, zero-downtime operations, and agent-aware serving so the same endpoint can handle both human users and autonomous agents efficiently. In one test, llm-d's prefix-aware router captured 97% of available cache reuse on an agentic coding workload, and IBM/Red Hat ran 3,000 concurrent software-engineering agents for 5 to 10 times less cost than using the same model as a hosted service.

IBM Research
Research· Important

New research: agents don't 'decide' to obey a prompt injection all at once — the choice unfolds as they reason

A new study questions the common belief that whether an AI agent falls for a prompt injection is settled the moment it reads the malicious text. The researchers built a branching-rollout technique on AgentDojo benchmarks: they replayed an agent's run up to the point it encounters an injected instruction, then let the rest of the episode play out many different ways to measure how much of the final outcome was already locked in versus still open. For a Qwen3 agent running without extended reasoning, 91% of the outcome was already determined at that moment; switching on reasoning ('thinking') cut that figure to 62%, showing the agent's compliance decision often keeps forming well after it first sees the attack. Enabling reasoning also cut Qwen3's susceptibility to successful attacks, but made two other tested models more vulnerable, and benchmark scores for reasoning agents flipped on a rerun as often as 35% of the time.

arXiv cs.CL
Research· Important· 🧪 Worth Testing

AWS introduces push-based KV transfer to cut latency in disaggregated vLLM inference

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.

AWS Machine Learning

Microsoft and NVIDIA publish joint framework for managing open-weight model risk

Microsoft and NVIDIA released a joint whitepaper, 'Risk Management for Open-Weight Models in Enterprise,' the first in a planned series offering enterprises a shared risk taxonomy and methodology for evaluating open-weight AI models. The paper argues that whether a model is open or closed-weight is not the key risk factor — what matters is the use case, deployment architecture, and surrounding safeguards. It organizes risks into five categories (Cybersecurity, Data Protection, Content, Human-AI Interaction, Bias) and maps evaluations to those risks, aligning with ISO standards and the NIST AI Risk Management Framework.

Microsoft Security
Research· Important

Google Research builds AI agents that design and run wet-lab experiments

Google Research describes new work on grounding AI agents in physical lab reality, using a digital-twin framework called VERID to let agents safely plan and execute liquid-handling robot protocols. Combined with closed-loop molecular design cycles for aptamers and proteins, the agents iteratively learned from wet-lab results, improving hit rates over multiple rounds and discovering single-digit nanomolar protein binders for a cancer-related target.

Google Research
Agents· 🧪 Worth Testing

Google Cloud outlines a three-layer agent architecture for high-compute, governed biotech workflows

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.

Google Cloud AI
Models· Important

Reflection releases Beam, a 501B open-weight MoE model with 1M-token context

Reflection, a new US AI lab, has launched Beam, its first model, as an open-weight mixture-of-experts system with 501B total parameters (23B active per token) and a 1M-token context window, released under Apache 2.0. The model is built for coding and agentic use cases, ships with a custom Rust-based inference harness, and has day-0 support in transformers, vLLM and SGLang. Reflection reports strong results on coding, reasoning and tool-calling benchmarks across BF16, FP8 and NVFP4 checkpoints.

Hugging Face

NVIDIA and AI4Bharat Release 2.8 Trillion-Token Indic Pretraining Corpus and Open Data Pipeline

NVIDIA, working with IIT Madras's AI4Bharat lab, is releasing Nemotron-pretraining-Indic-v1, a roughly 2.8 trillion token synthetic pretraining corpus covering 22 Indian languages, along with the open GPU-accelerated pipeline used to generate it. The corpus includes native-script data for all 22 languages and romanized text for twelve, built by translating curated English source material (web text, math, code, Q&A) using NeMo Data Designer and quality-checked with an MQM-inspired rubric. NVIDIA already used a 10-billion-token Indic subset for continued pretraining of Nemotron 3.5 Super VL, which showed measurable gains on Indic benchmarks.

Hugging Face
Models· Important· 🧪 Worth Testing

IBM combines transcription, decision-making and chat in a single Granite Switch model

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.

Hugging Face
Models· Important· 🧪 Worth Testing

Meta releases Muse Spark Open, an 816B-parameter open-weight multimodal MoE model

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.

Hugging Face

Apple Shows Trillion-Parameter-Class LLMs Running Locally on Mac Studio Clusters with MLX

Apple's MLX team published benchmarks showing large open-weight models — including a near-trillion-parameter MoE model called Muse Spark Open — running on Mac Studio hardware, both on a single machine and distributed across up to four Mac Studios using a new RDMA-over-Thunderbolt driver. The new M5 Ultra chip, with dedicated GPU Neural Accelerators and 1.2 TB/s memory bandwidth, delivers up to 4.6x faster time-to-first-token and 1.6x faster generation speed versus the previous M3 Ultra. For models too large to fit on one machine, MLX now supports pipeline and tensor parallelization across multiple Macs connected via Thunderbolt RDMA, letting a four-Mac-Studio cluster generate over 36 tokens per second on an 816B-parameter model.

Apple Machine Learning
Models· Important· 🧪 Worth Testing

Apertus 1.5 adds image/audio understanding, longer context and a thinking mode to the open 8B/70B models

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.

Hugging Face
Voice AI· 🧪 Worth Testing

Small Fine-Tuned Model Learns to Follow New Regulated Call Scripts Without Retraining

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.

arXiv cs.CL
Cyber Security· Important· 🧪 Worth Testing

GitHub swaps LLM-based secret scanner for a lightweight ModernBERT classifier

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.

GitHub
Models· Important· 🧪 Worth Testing

Liquid AI's new open-weight model runs agentic reasoning locally with just 2B active parameters

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.

Hugging Face
Agents· Important· 🧪 Worth Testing

Orca Security cuts natural-language query costs 90% using a staged Bedrock agent pipeline

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 Machine Learning
Research· 🧪 Worth Testing

AWS open-sources MoE kernel optimizations for vLLM, cuts latency and boosts throughput on H200

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).

AWS Machine Learning
Business· Important· 🧪 Worth Testing

NVIDIA Open-Sources Run:ai GPU Orchestration Platform

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.

NVIDIA Developer
Research· Important

IBM shows open-model AI agents can cut chip-design search costs by over 11x

IBM Research used a coordinated multi-agent 'agent factory' to explore hardware design optimizations for a quantum error-correction decoder, comparing proprietary and open frontier models under the same 100-hypothesis search budget. The open-model configuration, run on-premises via IBM's llm-d distributed inference framework, achieved a 52x speedup over baseline for about $26 in inference cost, versus $299 for a proprietary-model configuration that reached a higher 204x speedup. The study highlights that cache-aware routing and efficient serving (98% prefix-cache hit rate, ~$0.11 per million tokens) made the open-model approach dramatically cheaper while still finding valid, compact hardware designs.

IBM Research
Research· Important· 🧪 Worth Testing

Amazon's 'Priming' Turns Pretrained Transformers Into Efficient Hybrid Models for Under 1% of Training Cost

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.

Amazon Science

NVIDIA and Princeton Cut Decoding Bottlenecks in Hybrid SSM Models

NVIDIA, working with Princeton's Dao AI Lab, built ReplaySSM, a new way to store state in hybrid models that mix state-space (SSM) layers with attention layers. Instead of rewriting the entire state on every token, the method keeps a periodic checkpoint plus a short list of recent inputs, splitting the job of producing output from the job of updating memory. The result is roughly half the memory traffic, decode kernels running up to 1.80x faster at scale, and speculative decoding throughput more than doubling on 120B-class models, all while keeping accuracy close to full precision. The method already ships inside TensorRT-LLM, vLLM, and FlashInfer, and is running in production for GLM-5.3-Flash and Kimi-K3.

NVIDIA Developer
Voice AI· Important· 🧪 Worth Testing

Mistral releases open-source real-time Arabic speech-to-text model Voxtral Mini 4B Realtime Arabic

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.

Mistral AI (Hugging Face)
Models· Important· 🧪 Worth Testing

Google Open-Sources ML Drift, a New GPU Engine for On-Device AI Inference

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 Developers