Concept
SRAM
SRAM (Static Random-Access Memory) is the fast, on-chip memory that sits closest to a GPU's compute units, distinct from the much larger DRAM-based HBM (High Bandwidth Memory) that holds your model weights and activations. Think of it like a CPU's L1/L2 cache, except…
The rest of “SRAM” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→