MLOps news and analysis on Web Pulse: 3331 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
A hands-on one-semester course walks students through building a machine-learning compiler from scratch, progressing from elementwise operations to training a real LLM on GPUs. Over roughly ten weeks, students implement …
A developer self-hosting Langfuse discovered that tracing was enabled on only one of ten agent profiles, capturing roughly 7% of traffic — 618 events across 79 traces in four weeks — while the coding agent alone made 522…
C1 launched C1 LLM Gateway on Day 4 of its Launch Week, a policy-controlled endpoint that routes inference across supported public, private, and customer-controlled model deployments. The gateway ties each request to a p…
Arize's 2026 cost model breaks production evaluation spend into traffic volume × sampling rate × evaluation surfaces × evaluator cost plus human review and retention, while offline evaluation is dataset size × system var…
A developer released laya-evals, an open-source CI gate for LLM evaluation that combines rubric-based LLM-as-judge scoring, calibration auditing (Expected Calibration Error, Brier score, reliability bins), and a GitHub A…
Jaival Suthar released Knowledge Vault (M1), a local-first PDF retrieval system built on PyMuPDF text extraction, token-aware recursive chunking, BAAI/bge-small-en-v1.5 embeddings stored in Qdrant, and optional BAAI/bge-…
LiteLLM launched Lens on September 30th, a tracing and analysis product that uses AI agents to find recurring problems across agent runs, according to co-founder and CTO Ishaan Jaffer. Lens stores trace data in ClickHous…
A developer compared seven cloud sandbox and VM providers for hosting AI agents — machine0, OpenComputer, E2B, Daytona, Modal, Fly.io Sprites, and Vercel Sandbox — testing each SDK up to the API-key check as of September…
A developer audited 34 agent skill packages and found that a code-review tool returned a 100/100 health score and exit code 0 after being passed a nonexistent path, scanning zero files while reporting 'safe to merge.' Th…
A developer detailed a production-grade multi-agent RAG architecture built on Semantic Kernel, Azure Functions, and Redis Cache for a B2B SaaS client handling 1 million support tickets per day. The five-agent setup (Rout…
An engineering team describes six feedback loops spanning planning, coding, testing, review, release, and incidents that turn an AI coding agent's corrections into durable checks across the delivery pipeline. The approac…
Jevotron launched a command-line tool that scans CSV, YAML, JSON, TOML, text, and OBO files for field-level anomalies using the TypeSafe API, caching each successful assessment in SQLite so unchanged entries are not reas…
A developer built ClearPix, a static, backend-free watermark remover that runs ONNX Runtime Web inference entirely in the browser via WebGPU with a WASM fallback, so user images and videos are never uploaded. The enginee…
A developer documented a spec-driven, multi-agent workflow called BMAD for scaling agentic software development, in which a colleague named Vlad used the framework to refactor a monorepo CI/CD pipeline that had 90-minute…
Sail Research retired B3IT monitoring for the deepseek/deepseek-v4.1-flash endpoint on the fp4 provider as of 2026-10-03, citing insufficient border inputs, while LT tracking remains active. The endpoint's total tracked …
AWS published an implementation guide for a multi-agent contract intelligence pipeline on AgentCore, in which extraction agents use Amazon Bedrock foundation models to pull structured fields from vendor agreements, verif…
A developer's Kubernetes operator, pd-ratio-coordinator, failed to compile on its committed KRAG-1 branch, with two real bugs — a DeepCopy type mismatch in register.go and four unqualified Bottleneck constants in scaler/…
NVIDIA Dynamo-Triton now supports an end-to-end Hierarchical Sequential Transduction Unit (HSTU) generative recommender inference workflow via the NVIDIA recsys-examples repository, achieving best-case speedups of up to …
Carnegie Mellon University plans to integrate a new open-source book, "Agentic GPU Programming for MLSys," into its Machine Learning Systems course series, teaching a compiler-driven harness that lets coding agents write…
Researchers submitted Purlin, a scale-up GPU collective communication framework that separates orchestration from the datapath, to arXiv on 29 Sep 2026. Purlin specifies collectives as input/output layouts plus copy or r…