Report
AgentX disaggregated serving reportedly reaches 1.3 billion tokens per TCO dollar at hyperscaler volume pricing
SemiAnalysis says vLLM and Inferact achieved the result, four times better than the B300 aggregated configuration.
TLDR
SemiAnalysis says vLLM and Inferact achieved 1.3 billion tokens per dollar of total cost of ownership (TCO) using disaggregated serving on AgentX at hyperscaler volume pricing. It says that result is four times better than the B300 aggregated configuration.
Combined views
—
1 Source, first seen ago
