← 研踪 PaperTrailarXiv:2611.10845 · v1
Inference for Reasoning Models: Practical Lessons from Evaluation and Serving
首次提交 2026-11-08 00:43
版本更新 2026-11-08 00:43
雷达观测 2026-11-10 11:14
摘要
Running a language model involves more than its trained weights. The same model can receive very different benchmark scores, produce different answers, or cost more to serve depending on how it is evaluated and run. In one experiment in this book, changing only the maximum response length moved accuracy on a math benchmark from 0.08% to 93.18%. This book explains how inference settings shape the results we report and the systems we deploy. We begin with evaluation, including generation limits, answer extraction, scoring methods, and quantization. We then examine why outputs can change across batches, attention backends, and caching, even when sampling is disabled. The next chapters cover serving performance, including batching, memory capacity, latency, throughput, and cost. We also study structured outputs, tool calls, reasoning budgets, and long-context tasks, showing what these controls and benchmarks do and do not establish. The book concludes with practical guidance for recording inference runs, checking evaluations, estimating capacity, and comparing systems fairly. Written for researchers and engineers working with language models, it aims to make inference results easier to understand, reproduce, and trust.
作者备注:217 pages. Book, first edition, version 1.0 (August 2026). Published on Zenodo
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-08 00:43 · 最新观测版本
Inference for Reasoning Models: Practical Lessons from Evaluation and Serving
Running a language model involves more than its trained weights. The same model can receive very different benchmark scores, produce different answers, or cost more to serve depending on how it is evaluated and run. In one experiment in this book, changing only the maximum response length moved accuracy on a math benchmark from 0.08% to 93.18%. This book explains how inference settings shape the results we report and the systems we deploy. We begin with evaluation, including generation limits, answer extraction, scoring methods, and quantization. We then examine why outputs can change across batches, attention backends, and caching, even when sampling is disabled. The next chapters cover serving performance, including batching, memory capacity, latency, throughput, and cost. We also study structured outputs, tool calls, reasoning budgets, and long-context tasks, showing what these controls and benchmarks do and do not establish. The book concludes with practical guidance for recording inference runs, checking evaluations, estimating capacity, and comparing systems fairly. Written for researchers and engineers working with language models, it aims to make inference results easier to understand, reproduce, and trust.
查看此版本解读 →查看此版本原文 ↗