⚡Megatron LLM Hub
←返回搜索
Twitter

分析称 AMD 用 vLLM 跑 Kimi K3 每芯片每小时可赚约 3 美元

llm云
RT @SemiAnalysis_: PROFIT ALERT🚨: AMD @vllm_project can generate up to $3/hr/chip in pure profit serving the open-source Kimi K3 model, even after accounting for the rapid increase in chip rental prices post-Claude Code. Kimi K3 2.8T is a great model for AMD, as it has over 2.8 trillion parameters that can take advantage of AMD's 288GB per chip. B200 CANNOT fit Kimi K3 in a single server, so it has to use tensor parallelism or pipeline parallelism for communication across 400Gbit/s InfiniBand/Ethernet, which is 18x slower than the BW within an NVLink domain.