3 papers
cs.DC2026
Architecting for Hardware Diversity: Meta's End-to-End Co-Design for High-Performance AI Training on AMD GPUs
Haoyu Zhang, Arshad Rahman, Adnan Aziz +55
Meta deploys a heterogeneous fleet comprising NVIDIA GPUs, AMD GPUs, and proprietary MTIA accelerators to reduce costs and mitigate vendor lock-in. However, the extensive history o…
cs.DC2026
Coda: Exploiting Admission Flexibility for Coding-Agent Serving
Youhe Jiang, Fangcheng Fu, Binhang Yuan +5
Coding agents powered by large language models (LLMs) repeatedly alternate between model inference and tool calls, creating long-lived sessions with reusable key-value (KV) states…
cs.DC2026
Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving
Yi Xu, Ehsan K. Ardestani, Wenyin Fu +7
As serving capacity demand surpasses that of training, serving efficiency becomes increasingly important. Prefill-decode (P/D) disaggregation improves serving efficiency through sp…