Find articles, news, tools and templates by subject or by the work you need to do.
113 results for “Improve on-call workload” · 13–24
Commentary · Incident response ·
A mistaken target selection shows how an incident review can explain a responder’s choice and lead to a more useful interface improvement.
Read commentary: Why blameless reviews investigate the conditions around a mistakeCommentary · Engineering leadership ·
A vacation backup who can receive pages but cannot perform recovery shows why coverage must transfer access, knowledge and workload together.
Read commentary: Making time off workable for an SRE teamGuide · Engineering leadership ·
A chapter-level starting point for alerting, on-call coverage and postmortems, with examples of adapting the practices to local staffing and authority.
Read guide: Where to start with Google’s free SRE booksExplainer · Platform engineering ·
Infermeld makes a mixed-GPU llama.cpp launch inspectable. Its recorded failures show why separate device allocations and completed workload checks matter more than adding VRAM capacities.
Read explainer: How Infermeld runs one model across AMD and NVIDIA GPUsNews · Platform engineering ·
An eight-B200 test retained 96.1% to 98.2% of baseline output-token throughput with confidential computing enabled. Its software and workload define what that comparison covers.
Read news: NVIDIA measures the overhead of confidential inferenceNews · Platform engineering ·
The alliance supports storage, generation and flexible AI workloads as ways to change grid demand. For a scheduled evaluation, a safe pause can still miss the deadline the job serves.
Read news: AI energy alliance backs data centers that can vary grid demandNews · Observability ·
Kubernetes attributes connect agent calls to pods, workloads and paging routes. A processor migration can break those connections while telemetry still flows.
Read news: OpenTelemetry’s Kubernetes attributes processor reaches v1Explainer · Platform engineering ·
Power and cooling affect the work a GPU pool can sustain. Device signals, request completions and queue growth help distinguish a physical limit from a workload change.
Read explainer: GPU capacity depends on power and coolingExplainer · AI in production ·
Kimi K3 can keep a larger incident record in view. Its practical value depends on evidence handling, agent integration and the cost of useful investigation.
Read explainer: What Kimi K3’s million-token context offers SRE teamsExplainer · Platform engineering ·
A stalled rollout shows how platform repair and application recovery depend on different teams, with a handoff that keeps both investigations moving.
Read explainer: Where SRE and platform engineering need an explicit handoffGuide · AI in production ·
Follow a weight through a training update, save a tiny model, and learn how checkpoints, fine-tuning, LoRA and held-out evaluation fit together.
Read guide: What are model weights, and how does training change them?Guide · AI in production ·
Understand Hermes Agent, its origins, models, memory and skills. Choose a setup, try two checkable examples, and learn where its limits matter.
Read guide: Hermes Agent guide: what it is, when to use it, and how to get started