Systems and efficient execution · MLD-1317
VRAM
Memory associated with a graphics processor, used to store model state, activations, and temporary data.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Estimate whether a model and its cache fit on a GPU.
Original caveat
Weight size alone is not the full memory requirement.
Context and aliases
Level: Foundational. Stages: Training · Inference · Deployment.
Tags: DL · LLM · SLM · Systems.
Aliases: Video random-access memory · GPU memory.
Related concepts
Concepts linking here
Original references
- PyTorch Fully Sharded Data Parallel ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- vLLM documentation ↗ · Consulted
- Original reference URL ↗