Deepseek V4 Flash on a single RTX 6000 Pro - vLLM-Moet
英文标题：Deepseek V4 Flash on a single RTX 6000 Pro - vLLM-Moet
Wow... https://github.com/kacper-daftcode/vLLM-Moet Using this customized vllm provided as a docker, I'm able to run DS V4 Flash on a single RTX 6000 Pro (apparently it also works on a single 5090 - check his readme, but I haven't tried). Apparently this also works with GLM 5.2 (though you need at l
打开原文相关 2 · 机会 2
中文
Wow... https://github.com/kacper-daftcode/vLLM-Moet Using this customized vllm provided as a docker, I'm able to run DS V4 Flash on a single RTX 6000 Pro (apparently it also works on a single 5090 - check his readme, but I haven't tried). Apparently this also works with GLM 5.2 (though you need at l
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Wow... https://github.com/kacper-daftcode/vLLM-Moet Using this customized vllm provided as a docker, I'm able to run DS V4 Flash on a single RTX 6000 Pro (apparently it also works on a single 5090 - check his readme, but I haven't tried). Apparently this also works with GLM 5.2 (though you need at l