NVIDIA says RDMA cut DeepSeek-V4 Pro startup from 8 minutes to under 2
RisingSayak · x · 2026-07-25
NVIDIA says it cut DeepSeek-V4 Pro startup time from 8 minutes to under 2 minutes.
The improvement comes from moving weights over the fastest path to GPU memory with GPU-to-GPU RDMA. NVIDIA says the approach is implemented through ModelExpress (MX) inside NVIDIA Dynamo, and it also speeds up inference and RL post-training by reusing kernel caches and fetching updated weights efficiently.
Related event: NVIDIA Slashes DeepSeek-V4 Pro Startup Time to Under 2 Minutes(4 posts)→
More from Infra
- MiniMax H3 runs fully on a Galaxy S26: 5-second video with audio in ~7 minutes — BidFunny4862 · 2026-10-27
- Unconventional AI acquires inference chip firm NeuReality in 1,000x efficiency bid — NaveenGRao · 2026-10-27
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- RTX 5090 hits $7K as PC gaming community goes into 'denial' over AI boom — PAstynome · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27