The paper argues that large language model (LLM) providers, constrained by compute, often degrade service during congestion by routing queries to smaller models, cutting reasoning effort, or truncating context. It shows that this practice misrepresents costs because degraded answers can fail, leading to retries that inflate traffic or churn that erodes lifetime value. By modeling inference allocation with newsvendor, retry, and queueing frameworks, the authors derive a ‘shadow price of intelligence’ that quantifies the marginal value of each query, revealing that throttling under congestion acts as a demand lever rather than a cost lever.
By Elioth Sanabria
arXiv:2607. 17283v1 Announce Type: new Abstract: Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized.
By Param Chordiya
arXiv:2605. 16430v2 Announce Type: replace-cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure.
By Sophie Hao, William Merrill
The paper investigates whether training Mixture-of-Experts (MoE) routers can improve memory‑bandwidth locality on consumer GPUs. Using a new zero‑surgery telemetry tool, the authors measure that a large Qwen3‑235B model is bottlenecked by disk‑based expert access, and that an LRU cache can serve a majority of requests. They pre‑register experiments training 137 M‑parameter MoE models with locality‑aware losses, finding that while cache misses can drop up to 60 % (99 % static‑pin hit rate), every configuration fails to meet a strict 1 % perplexity threshold, indicating a tight coupling between cache efficiency and model quality.
By Shriniwas Ramesh Suram
arXiv:2609.23790v1 Announce Type: new
Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected toke...
By Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
By Sanjeev Rao Ganjihal
arXiv:2606. 21428v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference.
By Alfarizy Alfarizy, Hung Truong Thanh Nguyen, Ren\'e Richard, Roozbeh Razavi-Far, Hung Cao
arXiv:2609.13149v1 Announce Type: new
Abstract: For local large language model agents, active context is a scarce resource: memory capacity, prefill latency, cache growth, and service objectives all...
By Aditya Karnam Gururaj Rao, Arjun Jaggi
Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream each token's active experts from whichever tier holds them, and on consumer hardware most experts sit on an SSD far slower than RAM. We quantify this bandwidth wall on Qwen3-235B (Q4_K_M, 134 GB): measured decode is 0.
arXiv:2606. 18144v1 Announce Type: new Abstract: A robot's flash endurance is a non-renewable stock: every persisted write spends one of a few thousand program/erase cycles and never refills, yet no fielded robot memory system prices which memories are worth an erase cycle.
By Josef Liyanjun Chen
arXiv:2608. 11361v1 Announce Type: new Abstract: Tokenizer vocabulary size is a foundational design choice in large language model (LLM) infrastructure, yet it is typically fixed at training time based on convention rather than deployment analysis.
By Rima Mittal, Ankit Gubrani, Satyanarayana Kakollu
arXiv:2609.00710v1 Announce Type: cross
Abstract: An LLM application often sells or internally allocates several service products: a small or premium model, a short or long token cap, and possibly mu...
By Patrick Wong