New DeepSeek-V4-Flash-DSpark

Accelerated Computing DGX Spark / GB10 User Forum DGX Spark / GB10
1

Faster performance version of DeepSeek V4 Pro / FLash just dropped.

2

Do we need to enable speculative config in vllm for this or is it built-in to the model?

3

The weights incorporate the drafter but new support will be needed to inference engines to actually make use of them