Web Analytics Made Easy - Statcounter

Blog

When Bursty Traffic Makes LLM Inference Faster

event person Akira van de Groenendaal

Bursty arrivals usually cause a drop in performance and are seen as headaches in production systems. In this blog, we investigate a phenomenon where burstiness actually improves performance, uncovering what conditions produce this effect.

Read more →

Why FIFO Is (Almost) All You Need for Cache Eviction

event person Juncheng Yang

Cache eviction is usually presented as a ranking problem. LRU ranks objects by recency. LFU ranks them by frequency. More advanced algorithms combine several signals, adapt their parameters, and maintain increasingly sophisticated data structures to decide which object is least valuable.

Read more →

MorphServe: Making Model Precision Elastic for Bursty LLM Serving

event person Juncheng Yang

Most LLM servers treat a deployed model as fixed: its weights have one precision, its KV cache has one memory budget, and both remain unchanged until the process restarts.

Read more →