# GEMM Compute Scaling vs GEMV Memory-Bandwidth Bounds > Source-anchored research for GEMM Compute Scaling vs GEMV Memory-Bandwidth Bounds. Run status: COMPLETED. Parent: [Local Inference Micro-Architectures: Signaling, Quantization Superblocks, and Kernel Pipeline Scheduling](https://llms-explorer.com/tree/inference-microarchitectures-and-kernel-pipelines/) · 1 facets · 2 facts · page: https://llms-explorer.com/tree/gemm-compute-scaling-vs-gemv-memory-bandwidth-bounds/ ## Facts and statements - Prompt pre-fill evaluates GEMM operations where high arithmetic intensity (FLOPs/byte > 100) saturates GPU tensor cores and scales linearly with compute clock frequencies. (high confidence) — [source](https://github.com/vllm-project/vllm) - Auto-regressive decoding executes GEMV operations with minimal arithmetic intensity (FLOPs/byte approx. 1), causing GPU compute ALUs to sit idle while awaiting memory bus DRAM/GDDR reads. (high confidence) — [source](https://github.com/vllm-project/vllm)