From the 1 of 8 linked papers with an AI index.
8 papers
Zellige: Moldable Sequence Placement for Mixed Image-Video DiT Training
Guangyu Xiang, Xueze Kang, Minwei Zhao +4
High-quality video generation requires training Diffusion Transformers (DiTs) jointly on image and video data, posing a mixed-length sequence training problem across GPUs. Existing…
Xema: Efficient Diffusion Serving through Fine-Grained Memory Management and Auto-Configuration
Xueze Kang, Guangyu Xiang, Suyi Li +4
Xema is a system that reduces GPU memory usage for diffusion model serving by analyzing tensor lifetimes to apply targeted memory mitigation and by planning parallelism and concurr…
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding
Guangyu Xiang, Xueze Kang, Lin Zhang +4
LLM serving is increasingly dominated by long and dynamic decode workloads from agents, reasoning models, and extended conversations. When bursty long-context demand exceeds deploy…
ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling
Xin He, Shunkang Zhang, Kaijie Tang +8
Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many…
On the Spectral Flattening of Quantized Embeddings
Junlin Huang, Wenyi Fang, Zhenheng Tang +5
Training Large Language Models (LLMs) at ultra-low precision is critically impeded by instability rooted in the conflict between discrete quantization constraints and the intrinsic…
Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
Xinglin Pan, Shaohuai Shi, Wenxiang Lin +4
The mixture-of-experts (MoE) architecture scales model size with sublinear computational increase but suffers from memory-intensive inference due to KV caches and sparse expert act…