Idle models might be smarter: a musing on GEMV vs GEMM under low concurrency

karminski3 · x · 2026-09-17

An interesting speculation: when a model is completely idle (concurrency of 1, a single request), extremely quantized inference may take the GEMV path instead of GEMM, incurring lower accumulated precision loss — so the model might effectively be smarter. An unverified technical musing on the relationship between serving load, quantization, and precision.

Original post →

More from Infra

Infra channel →