open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity

docs(ms-ai-architect): KB-refresh MEDIUM 18/33 — load-testing: PTU min deployment Global/Data Zone 15 (increment 5); 50 kun Regional

Browse source
This commit is contained in:
Kjell Tore Guttormsen 2026-06-24 11:38:24 +02:00
commit 58509c918c
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
skills/ms-ai-security/references/performance-scalability/load-testing-ai-services.md
View file

@ -1,6 +1,6 @@
# Load Testing AI Services # Load Testing AI Services
**Last updated:** 2026-02 **Last updated:** 2026-06-24
**Status:** GA **Status:** GA
**Category:** Performance & Scalability **Category:** Performance & Scalability
@ -344,11 +344,14 @@ def forecast_ptu_requirements(
ptus_needed = required_tpm_with_growth / tpm_per_ptu[model] ptus_needed = required_tpm_with_growth / tpm_per_ptu[model]
# Round opp til nærmeste deployable enhet # Round opp til nærmeste deployable enhet.
min_deployment = 50 if "mini" not in model and "nano" not in model else 25 # Global & Data Zone Provisioned (anbefalt default): minimum 15 PTU, increment 5 for alle GPT-/o-modeller.
# Regional Provisioned: minimum 50 (gpt-4.1/o3/gpt-4o), 25 for mini/nano-modeller.
min_deployment = 15
increment = 5
ptus_deployed = max( ptus_deployed = max(
min_deployment, min_deployment,
((int(ptus_needed) // min_deployment) + 1) * min_deployment ((int(ptus_needed) // increment) + 1) * increment
) )
return { return {