Przemyslaw Forys
- Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
2025/09/11 by Haoran Wu, Wu, Haoran, Can Xiao +31 · 1 voice · 2 citations
Computer Science · #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #cs.AR
- When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference
2026/08/04 by Przemyslaw Forys, Haoran Wu, Can Xiao +8
Computer Science · #cs.DC