BestHub
Sign in
Tagged articles

MiMo-V2.5-Pro

2 articles · Page 1 of 1
Xiaomi Tech
Xiaomi Tech
Jun 9, 2026 · Artificial Intelligence

How Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed Achieves 1000 TPS on a 1‑Trillion‑Parameter Model

Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed mode breaks the 1000 tokens‑per‑second barrier for a 1‑trillion‑parameter model by combining FP4 expert‑only quantization, DFlash block‑masked speculative decoding, and TileRT’s ultra‑low‑latency GPU system, and the API is now available through a limited‑time trial.

AI inferenceDFlashFP4 Quantization
0 likes · 13 min read
How Xiaomi’s MiMo‑V2.5‑Pro UltraSpeed Achieves 1000 TPS on a 1‑Trillion‑Parameter Model
Amazon Cloud Developers
Amazon Cloud Developers
Apr 28, 2026 · Cloud Computing

How AWS Achieved Day‑0 Adaptation of Xiaomi’s MiMo‑V2.5‑Pro on Trainium

AWS has completed a Day‑0 rapid adaptation of Xiaomi’s open‑source MiMo‑V2.5‑Pro model, enabling developers worldwide to run the 1‑trillion‑parameter, 1‑million‑token model on Amazon Trainium chips with high‑throughput, low‑latency inference via Neuron SDK integration, and offers three deployment paths—EC2, SageMaker, and EKS/ECS.

AI inferenceAWSAmazon Trainium
0 likes · 6 min read
How AWS Achieved Day‑0 Adaptation of Xiaomi’s MiMo‑V2.5‑Pro on Trainium