You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Analytical benchmark connecting pipeline parallelism and KV cache management: bubble-time overlap for disaggregation, prefix reuse tax of PP stages, and tiering speedup across NVLink, InfiniBand, and PCIe
Analytical benchmark for sliding window attention KV cache management: quality vs window size tradeoffs, SWA vs eviction comparison, prefix sharing interaction, and operational window recommendations across four attention distributions
Analytical benchmark connecting tensor parallelism and KV cache management in LLM serving: GQA sharding regimes, all-gather vs recompute tradeoffs, PCIe viability, and operational decision matrix across NVLink, InfiniBand, and PCIe