Live

Search “h3”

Found 3 items · updated 01:10

Nov 12Thu

Nov 12Thursday

16:45
vLLM Blog· 16:45Featured6060
vLLM-Omni supports MiniMax H3-Image on NVIDIA Vera Rubin, generating 4K in 0.87 seconds
The vLLM-Omni team has integrated MiniMax H3-Image into NVIDIA Vera Rubin. With a four-card SP4 configuration, the native 4096×4096 image-to-image short prompt benchmark median latency is 0.87 seconds, and the throughput of four copies SP1×DP4 reaches 6115 images per hour.
Guides #Tutorials #Engineering #Reasoning

Oct 9Fri

Oct 9Friday

03:01
Comfy Blog· 03:017070
How to use MiniMax H3 to generate real-time video on a single GPU
Using the FastVideo FastH3 V2 checkpoint, it generates 15-second 448×256 resolution video on a single RTX 5090 GPU through optimizations like four-step sampling, sparse attention, small text encoders, small checkpoints, and fused FP4 MLP. VRAM requirements are reduced from 80GB to <30GB; this custom Comfy node is open-sourced and can be deployed by requesting GPU and models via Comfy API.
Guides #Tutorials #Reasoning #Video

Oct 16Fri

Oct 16Friday