capacity-planning

Tag

Cards List
#capacity-planning

AI-driven Thermal-aware Data Center Capacity Planning

arXiv cs.LG ↗ · 2026-10-05 Cached

An arXiv paper presents an AI-driven framework for thermal-aware data center capacity planning that predicts temperatures in milliseconds, achieving high accuracy on unseen designs with a 10,000x speedup over high-fidelity CFD simulations, enabling real-time optimization of workload distribution and HVAC cooling for LLM-driven data centers.

0 favorites 0 likes
#capacity-planning

@rohanpaul_ai: Big number. Anthropic's IPO prospectus puts its potential SpaceX compute bill at $84.5B, nearly double SpaceX's earlier…

X AI KOLs Following ↗ · 2026-09-29 Cached

Anthropic's confidential IPO prospectus reveals a potential $84.5 billion compute bill with SpaceX through 2029, nearly double previous estimates, with the ability to cancel most spending with 90 days' notice.

0 favorites 0 likes
#capacity-planning

The August 17 outage, and the work ahead

Hacker News Top ↗ · 2026-08-20 Cached

GitHub experienced a significant outage on August 17 due to capacity failures, disrupting services for hours. The company is accelerating efforts to improve infrastructure reliability and scale systems to handle growth.

0 favorites 0 likes
#capacity-planning

Lifecycle-Optimal Tokenization: Vocabulary Size as a Deployment-Regime-Dependent Infrastructure Parameter

arXiv cs.LG ↗ · 2026-08-13 Cached

This paper argues that the optimal tokenizer vocabulary size is not fixed but depends on the deployment regime, such as batch size and inference volume. Through roofline analysis and experiments on A10G and A100 GPUs, it shows the lifecycle-optimal vocabulary can shift by up to 16x between on-device and datacenter serving, with minimal quality impact.

0 favorites 0 likes
#capacity-planning

Lorenz and Little: How Much Does Your Tail Cost?

Lobsters Hottest ↗ · 2026-07-29 Cached

Explores how to quantify the contribution of each latency percentile to mean latency using the Lorenz curve, and connects it to concurrency via Little's law, demonstrating that tail latency often dominates cost and capacity.

0 favorites 0 likes
#capacity-planning

Using the Gini Coefficient to Plan Edge Capacity

Lobsters Hottest ↗ · 2026-06-24 Cached

Fastly uses the Gini coefficient, a macroeconomic metric for inequality, to model traffic inequality and plan edge capacity, outperforming complex ML models for rare but critical events.

0 favorites 0 likes
#capacity-planning

Queues Don't Fix Overload (2014)

Hacker News Top ↗ · 2026-06-09

An article explaining why queues are not an effective solution for handling system overload and discussing better approaches.

0 favorites 0 likes
#capacity-planning

@levie: Token costs will become a dominant topic in enterprises going forward with AI. Just got out of a dinner with many Fortu…

X AI KOLs Following ↗ · 2026-05-20 Cached

Token costs are emerging as a key enterprise concern for AI adoption, with CIOs struggling to manage spending across different models and use cases. OpenAI announced Guaranteed Capacity to address long-term compute access.

0 favorites 0 likes
← Back to home

Submit Feedback