5 papers
Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework
Leonid Kondrashov, Hongrui Liu, JooYoung Park +14
Autonomous agents challenge conventional LLM serving by coupling repeated inference with persistent context and sandboxed tool execution. We present Aries, a full-stack experimenta…
TileSight: A First-Principles Tile-Centric Analytical GPU Performance Model from Cores to Clusters
Zhiwen Mo, Yu Cheng, Lei Wang +12
Recent GPU programming frameworks such as Triton, TileLang, and CUDA Tile adopt tiles as first-class primitives, making tile-centric programming the prevailing approach for high-pe…
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache
Dayou Du, Shijie Cao, Jianyi Cheng +3
The growth of long-context Large Language Models (LLMs) significantly increases memory and bandwidth pressure during autoregressive decoding due to the expanding Key-Value (KV) cac…
TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity
Ruiqi Lai, Hongrui Liu, Chengzhi Lu +6
The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autosc…
WaferLLM: Large Language Model Inference at Wafer Scale
Congjie He, Yeqi Huang, Pei Mu +5
Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-c…