AMD Instinct MI355X reportedly posts ~42% lower p99 latency in RAG testing against Nvidia HGX B200
AMD says Signal65’s RAG testing, hosted via TensorWave, found the MI355X had roughly twice the concurrent-user headroom before breaching the evaluated SLA.
TLDR
AMD says its Instinct MI355X delivered ~42% lower p99 latency and roughly 2x the concurrent-user headroom before breaching the evaluated SLA in Signal65 RAG testing hosted via TensorWave. Signal65’s linked evaluation compares the MI355X platform with Nvidia HGX B200.
Combined views
7.7K
1 Source, first seen 2h ago

