Comment by echion
7 days ago
> you can combine Spark with M3U, the former streaming the compute, lowering TTFT, the latter doing the token generation part
Are you doing this with vLLM, or some other model-running library/setup?
7 days ago
> you can combine Spark with M3U, the former streaming the compute, lowering TTFT, the latter doing the token generation part
Are you doing this with vLLM, or some other model-running library/setup?
They're probably referencing this article: https://blog.exolabs.net/nvidia-dgx-spark/