DeepSeek V4 Flash 284B (13B active)
on NVIDIA H200 · SGLang
Summary
User reports DeepSeek V4 Flash with DSpark speculative decoding on an HGX-H200 with 4 GPUs at TP=4 via SGLang.
Setup compares the marlin and flashinfer MoE backends.
DSpark is faster than EAGLE: 3.2x at bs=1 and +46% throughput at bs=24. The user reports TTFT and accept length benchmarks.