SemiAnalysis(@SemiAnalysis_):TOKENMAXXING: @vllm_project and @inferact achieve 1.3 BILLION tokens per $ of TCO (hyperscaler volume pricing) via disaggregated serving on AgentX. This result is 4x better than the B300 aggregated configuration.

2026.10.17 19:00

TOKENMAXXING: @vllm_project and @inferact achieve 1.3 BILLION tokens per $ of TCO (hyperscaler volume pricing) via disaggregated serving on AgentX. This result is 4x better than the B300 aggregated configuration.

轉發到社區

熱門用戶

465.6K 粉絲

4.2M 粉絲

1.9M 粉絲

101.3K 粉絲

257.6K 粉絲

37.3K 粉絲

547.1K 粉絲

182.1K 粉絲

28.3K 粉絲

574K 粉絲

134.9K 粉絲

26.4M 粉絲

11K 粉絲

232.6K 粉絲

110.5K 粉絲