1 dépôt
Sizes multi-pool LLM GPU fleets against latency targets using discrete-event simulation without upfront hardware profiling.
Distinct from Multi-Vehicle Fleet Coordinators: No candidate covers LLM GPU fleet capacity simulation; closest are vehicle or server fleet coordinators.
Explore 1 awesome GitHub repository matching devops & infrastructure · GPU Fleet Capacity Simulators. Refine with filters or upvote what's useful.
Sizes multi-pool LLM GPU fleets against latency targets using discrete-event simulation.