From the 1 of 4 linked papers with an AI index.
4 papers
Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit
Xiaomi MiMo Team, Anqi Liu, Aoxin Ma +28
The paper describes a production-ready inference system for the MiMo-V2.5 large language model family that combines hybrid sliding window attention, sparse mixture-of-experts, and…
WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
Chiheng Lou, Sheng Qi, Rui Kang +5
Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems impr…
MiMo-V2-Flash Technical Report
Core Team, Bangjun Xiao, Bingquan Xia +123
We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-…
HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds
Chiheng Lou, Sheng Qi, Chao Jin +5
With the proliferation of large language model (LLM) variants, developers are turning to serverless computing for cost-efficient LLM deployment. However, public cloud providers oft…