Kimi K3 full model running on 16x GB10 cluster at 20+tps
英文标题：Kimi K3 full model running on 16x GB10 cluster at 20+tps
Kimi K3 full model running on 16x GB10 cluster at 20+tps average (llama-benchy coherent corpus) 38tps peak, 750tps prefill. This is the first run of full k3 with dspark on my cluster. I will be doing some tests and try tp speed this up. As soon as it looks ready I'll publish the vllm image and
打开原文相关 2 · 机会 0
中文
Kimi K3 full model running on 16x GB10 cluster at 20+tps average (llama-benchy coherent corpus) 38tps peak, 750tps prefill. This is the first run of full k3 with dspark on my cluster. I will be doing some tests and try tp speed this up. As soon as it looks ready I'll publish the vllm image and
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Kimi K3 full model running on 16x GB10 cluster at 20+tps average (llama-benchy coherent corpus) 38tps peak, 750tps prefill. This is the first run of full k3 with dspark on my cluster. I will be doing some tests and try tp speed this up. As soon as it looks ready I'll publish the vllm image and