Tag: 1M-token context
-
NVIDIA Rubin CPX: GDDR7 Prefill Offload Reshapes TCO
NVIDIA Rubin CPX moves prefill to a GDDR7-backed accelerator, disaggregating inference to cut HBM exposure, densify liquid-cooled racks, and improve…
NVIDIA Rubin CPX moves prefill to a GDDR7-backed accelerator, disaggregating inference to cut HBM exposure, densify liquid-cooled racks, and improve…