Layer-Streaming Telemetry Harness
Benchmark massive MoE LLMs under strict 0GB VRAM limits
Layer-Streaming Telemetry Harness이란?
An open-source MIT diagnostic tool to track peak system RAM, active VRAM allocation, and data-transfer layer execution when offloading extreme 284B parameter models onto commodity hardware footprints. Built for hardware-agnostic architecture audits.
스크린샷
?
아직 댓글이 없어요. 가장 먼저 남겨보세요!
Layer-Streaming Telemetry Harness에 대한 X의 실제 대화
X에 게시