Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Inference Optimization
/
Capacity Planning
Capacity Planning
Subtopic
4 questions
Questions tagged with Capacity Planning — part of Inference Optimization.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Estimate the RAM cost of an HNSW index over 100M vectors at 1024 dimensions with M=32, including graph overhead.
Short Answer
Hard
·
Qual 4.0
Pinecone
At batch 16 and 4k context with FP8 weights, which model still fits on one 80 GB H100?
Multiple Choice
Medium
·
Qual 4.0
Given a TPM rate limit, how do you compute supportable concurrent users for a feature?
Short Answer
Medium
·
Qual 4.0
OpenAI
Predict supportable concurrent-user count under a 200k TPM rate limit
Predict Output
Medium
·
Qual 4.0
OpenAI