GuidePlatform engineering
Disruption budgets and the capacity left behind
Plan an inference-service node drain with a scoped disruption budget, replacement-capacity checks and a practical maintenance worksheet.
AIOps
AI in production: tools, operating patterns, costs, and failure modes.
TensorRT speeds up one video by using eight GPUs
NVIDIA reports generation falling from 156.6 to 34.2 seconds on its example workload. The eight-device layout also changes how much capacity remains for other requests.
NewsAI in production
SWE-Serve tests coding agents through live inference
SWE-Serve checks coding-agent patches through a running SGLang server. In NVIDIA’s experiment, adding live-serving checks reduced the pass rate for the same patches.
NewsAI in production
Antigravity brings local models to its agent SDK
Antigravity’s SDK supports Gemma through LiteRT and compatible local model servers. A hybrid cloud planner offers another arrangement, with filenames and task descriptions sent off-device.
GuideAI in production
Prompt caching: measure the cost of useful work
What prompt-cache hits save once retries and failed work are included in task cost, with a local calculator and ledger.
NVIDIA measures the overhead of confidential inference
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.
NVIDIA Topograph maps GPU connections for workload placement
Topograph publishes discovered topology as Kubernetes labels or Slurm configuration. Placement policies can use that map to trade a shorter communication path against a longer queue.
NewsAI in production
GPT-6 Sol and Luna change the agent cost calculation
GPT-6 Sol and Luna combine lower token rates with cache-write and cache-read pricing. A repeated prompt can cost less even though its first cached write carries a premium.
GuideAI in production
How to evaluate incident-response agents
Build repeatable cases and check recovery independently, with a runnable Python grader.
AI energy alliance backs data centers that can vary grid demand
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.
NewsAI in production
Claude adds on-demand compaction for long-running agents
Claude’s on-demand compaction lets an application replace older conversation history with a signed summary. A conditional restart shows why the summary must preserve relationships between instructions.
NewsAI in production
Claude’s Chrome transcripts enter the enterprise audit trail
Claude Enterprise’s Compliance API beta now includes Chrome-session transcripts. Tool exchanges help locate an attempted action; the destination’s records establish whether it took effect.