MLOps news and analysis on Web Pulse: 3397 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
A developer argues that free LLM inference lanes are often the wrong choice because the real cost is occupied time, not token price. The writeup proposes a small Python break-even model that compares token cost plus bloc…
A developer argues that coding-agent patches should be rejected unless they come with a replay file that reconstructs the same side effects from stored inputs, rather than relying on a scrolling demo or a green terminal …
A developer at Meraki is Love described a set of verification practices for directing AI coding agents on live production systems, warning that green test suites and agent progress reports can mask silent failures such a…
A developer has published a fail-closed egress checklist for teams shipping coding agents into shared CI or shared machines, requiring every filesystem root, network host, and executable an agent can reach to be named in…
A developer documented migrating an AWS EC2-hosted MCP server for managing Gemma 4 E2B on a vLLM deployment from the MCP Python SDK 1.x (FastMCP) to 2.x (MCPServer). The migration was prompted by an unbound mcp dependenc…
Atomic Chat published a guest blog guide on selecting local large language models, recommending that users start with a GGUF Q4_K_M quantization if it fits their hardware. The guide provides memory-estimation formulas, n…
A developer behind Statewave argues that RAG and agent memory are distinct patterns that are frequently conflated, noting that RAG retrieves content an agent doesn't already know while memory retrieves context the agent …
A developer published a teaching lab that uses a simple "file fence" — a two-path allowlist plus a git diff checker — to stop AI coding agents from expanding a one-line timeout fix into an unrequested Redis cache subsyst…
OpenTelemetry graduated as a CNCF project in May 2026, making it the de facto observability standard and largely solving the instrumentation lock-in problem that defined the early 2020s, according to Dash0's 2026 blog po…
Llm-d is a Kubernetes-native distributed inference serving stack, released open source under Apache 2.0, that adds inference-aware orchestration on top of vLLM and Kubernetes without replacing either. The stack introduce…
The autofinetune project applies autonomous research loops to LLM post-training, using Google's Tunix library, Gemma models, and Cloud TPUs orchestrated with Antigravity CLI and Gemini Flash 3.7. In a supervised fine-tun…
A developer re-ran an identical A/B test of 41 AI tool descriptions and found the same 89/96 score both times, yet two individual cases flipped in opposite directions, revealing a noise floor of about 2 cases that the ag…
Swiss company SOKKAN Inference launched a sovereign "Swiss" inference tier running entirely on four Intel Arc Pro B60 GPUs in Meyrin, Geneva, with no NVIDIA hardware, serving gpt-oss-20b, Qwen3-Coder-30B-A3B, and Qwen3-N…
GKE clusters average just 8% CPU and 6% GPU utilization, while EKS clusters average 5% GPU and AKS clusters average 2% GPU, according to the Cast AI 2026 State of Kubernetes Optimization Report, indicating that over-prov…
Average CPU utilization across Amazon Elastic Kubernetes Service (EKS) clusters has fallen to 8% in 2026 from 10% in 2025, with 69% of provisioned CPU now completely unused, up from 40% year-over-year, according to the C…
A developer outlines engineering strategies for moving generative AI applications from prototype to production, arguing that the gap between a working demo and a resilient system is one of engineering discipline rather t…
Ory released Ory Lumen, an open-source local semantic code search engine that runs as an MCP server alongside Claude Code and cut Claude Code runtime by up to 53% and API costs by up to 39% in SWE-bench-style benchmarks.…
LinkedIn published details of a multi-teacher distillation pipeline that trains a 0.6B-parameter job-search ranking model roughly 8x faster, using a custom SGLang-based framework that serves teacher models directly in th…
The average production Kubernetes cluster runs at just 8% CPU utilization, according to the Cast AI 2026 State of Kubernetes Optimization Report, even as 88% of organizations report year-over-year increases in Kubernetes…
A developer built InfraOS AI, an open-source DevOps platform that connects to Kubernetes clusters and layers natural-language AI on top of pods, deployments, events, and Prometheus metrics. The tool answers plain-English…