AI Infrastructure news and analysis on Web Pulse: 34532 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
A developer demonstrated a privacy-first pipeline for fine-tuning Meta's Llama-3-8B on a decade of personal health reports using Apple's MLX framework and LoRA adapters, running entirely on a MacBook without sending data…
Proxy-GLS Public (api-public.proxy-gls.de5.net), an API relay tied to the GLS Group logistics company, was flagged as degraded by Uprouter's monitoring probes 16 minutes before publication, with 135ms latency after rough…
The House is expected to vote this week on the Ratepayer Protection Act, a bipartisan bill sponsored by Colorado Republican Rep. Gabe Evans that would require large-load data centers to be 100% responsible for the full i…
At the AI Infra Summit, AMD argued that AI infrastructure should be designed around adaptability rather than any single chip or fabric, citing three auditable properties — adaptable, economical and open — as the way to p…
Coroot and Percona announced a partnership at Percona Live 2026 in Amsterdam to deliver Coroot Percona Edition, extending observability for Percona customers beyond advanced database monitoring to full infrastructure vis…
AMD reported leadership scores and expanded benchmark coverage in MLPerf Inference v6.1, whose results were released on September 16, 2026. AMD and its partners submitted validated results across dlrm-v3, llama2-70b, gpt…
AMD published a step-by-step recipe for reproducing its MLPerf Inference v6.1 submission results on AMD Instinct MI355X, MI350X, and MI350P GPUs, marking the company's fifth consecutive round of MLPerf Inference particip…
The open-source Rust inference library behind the NobodyWho Chat test app can register for OS memory-warning signals to automatically unload LLM models before Android and iOS Out Of Memory killers terminate the app, acco…
Firebase AI Logic now runs developer-written Cloud Functions before and after every Gemini generateContent request, per Firebase's Sept. 10, 2026 release note. The beforeGenerateContent and afterGenerateContent triggers …
Agnes AI released Agnes-3.0-Flash Preview, a 33-billion-parameter open-weight multimodal language model under an Apache 2.0 license with a 262,144-token context window and a hybrid attention architecture. Of the model's …
An MLX-based parallel constrained decoding engine for Apple Silicon evaluates every JSON schema field in a single forward pass, cutting structured extraction latency 5.6x to 7.0x versus standard autoregressive JSON gener…
Weaviate 1.39 added 4-bit Rotational Quantization (RQ4) to its vector search engine, delivering similar recall to 8-bit RQ with a 45% heap reduction, according to the company's engineering blog. The release also added SI…
AMD published a step-by-step FlyDSL workflow for implementing a custom diffusion attention kernel, targeting vLLM's TiDAR (Think in Diffusion, Talk in Autoregression) mode with paged KV caches and scratch storage for spe…
OpenAI's GPT-Live 1, a full-duplex voice model that can listen and speak simultaneously, is now available on Vercel's AI Gateway. The model removes turn detection so users can pause, interrupt, or add detail while GPT-Li…
Edge0, an open-source framework posted to arXiv on September 16, 2026, reports running a 4-bit Qwen3.6-35B-A3B mixture-of-experts model at 20.4 tokens per second inside 2.9 GiB of peak active memory on a 24 GB Mac mini b…
SigNoz published a guide for monitoring self-hosted SGLang inference servers by sending Prometheus metrics and OpenTelemetry request traces to its observability platform. The setup requires launching SGLang with the --en…
EnCharge AI posted an on-site AI Software Engineer, Agent Harness role in Bengaluru, Karnataka, with remote-friendly options across India, seeking 10+ years of software engineering experience in backend systems or ML inf…
The U.S. House approved a bill by a vote of 417-3 on Wednesday that would require state utility regulators to consider charging artificial intelligence data centers the full cost of the new power and transmission upgrade…
A RoboKrunch teardown compares NVIDIA's newly announced Jetson Orin Nano 2, which offers 78 TOPS but won't ship until H1 2027 at an unannounced price, against Orange Pi's Rockchip RK3588-based Orange Pi 5 Max, which deli…
VLLM contributor mmastrac opened a pull request adding a "Jev-like" structured generation mode for the DiffusionGemma model, retitling it from a work-in-progress draft to "[Core] structured generation mode for DiffusionG…