Unverified50% confidenceBenchmarkExact time
The server measured a power consumption of 700–900 watts during the prefill phase and 500–600 watts during the decoding phase.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/13/2026
First Seen
Valid until: 12/12/2026
Sources
Related Entities
Related Claims
Unverified单台DGX H100服务器满负荷功耗达10.2千瓦，推动单机柜功耗从历史均值5-7千瓦攀升至100千瓦以上70% similarUnverifiedUnder a 45nm process, a single 32-bit floating-point multiplication consumes approximately 3.7pJ of energy, reading 32-bit data from off-chip DRAM consumes approximately 640pJ, and on-chip SRAM access requires approximately 5pJ.66% similarUnverifiedFor a typical 70-billion-parameter model, the KV cache occupies approximately 0.5 MB of memory per token, and generating 100,000 tokens requires carrying 50 GB of cache.65% similarVerifiedThe KV Cache of a 70B-parameter model with 128K context support can require hundreds of gigabytes of VRAM at full load, exceeding the 80GB VRAM capacity of a single H100.64% similarUnverifiedTaking Llama-3 70B as an example, the prefill stage for processing 32K tokens on an A100 80GB GPU takes approximately 800–1200ms, while processing 2K tokens takes only about 50ms.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/919201API
curl https://kongchang.com/api/v1/knowledge/claims/919201MCP
get_claim(id=919201)