The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The paper presents a Pareto atlas of LLM inference optimizations, mapping cost, quality, and latency trade‑offs for Qwen2.5‑7B‑Instruct on L4, A100, and H100 GPUs. Using 54 measured configurations and a calibrated simulator, it identifies 18 of 36 setups on the Pareto frontier, showing that combined methods outperform single ones. Quality tests reveal that AWQ 4bit and FP8 weights offer significant latency reductions while largely preserving accuracy, but naive FP8 KV caching fails to answer any questions correctly.
arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.
The paper examines test‑time scaling (TTS) methods that use extra inference compute to improve language model outputs. Across five open‑ended benchmarks—medicine, law, finance, general chat, and creative writing—the study finds that increasing exploration (generating more candidates) consistently yields better top candidates, but exploitation (selecting the final output) remains weak due to poor reward‑model correlation. Only the Fusion approach, which synthesizes candidates, reliably improves results, yet it recovers only about 40% of the potential quality, indicating that the bottleneck lies in choosing from the candidate pool rather than generating it.
arXiv:2608.22048v1 Announce Type: new Abstract: Large language models are increasingly deployed on local hardware for privacy, cost, and accessibility reasons. Yet many evaluations emphasize accuracy...
Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost?
arXiv:2609.07966v1 Announce Type: new Abstract: Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-cont...