sm120

Tag

Cards List
#sm120

@Hikari_07_jp: I got DeepSeek-V4-Flash MTP speculative decoding actually working on 2× RTX PRO 6000 +38% single-stream throughput. It …

X AI KOLs Timeline ↗ · 2026-06-24 Cached

Achieved DeepSeek-V4-Flash MTP speculative decoding on 2× RTX PRO 6000 with a 38% throughput increase by fixing a mis-routed quantization format issue.

0 favorites 0 likes
← Back to home

Submit Feedback