Unverified50% confidenceFactExact time
单Token生成的算术强度约为1 FLOP/Byte，导致GPU计算单元利用率不到1%
1
Sources
50%
Confidence
Long-term
Relevance
8/23/2026
First Seen
Sources
Related Entities
Related Claims
Unverified对于一个100万面的模型，LOD1可简化至25万面、LOD2简化至6万面，远距离渲染时GPU负载可降低75%以上67% similarUnverifiedA new computer based on coupled oscillators consumes only one-thousandth the power of a traditional GPU, with approximately 6.7% performance loss, and is fully open source.65% similarUnverifiedLarge model inference is typically memory-bandwidth-bound; the computational intensity of llama-2-70B inference is approximately 1–2 FLOP/Byte, far below the H100 peak computational intensity threshold of approximately 120 FLOP/Byte.65% similarUnverifiedQuantization reduces VRAM usage to 1/4 or 1/8 of the original while retaining most model capabilities.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789730API
curl https://kongchang.com/api/v1/knowledge/claims/789730MCP
get_claim(id=789730)