{"product_id":"138387","title":"LLM in Production ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jXPB8mxn8vUenFP0XDyMOFxApoxex.png?v=1765062766\" style=\"max-width:100%;max-height:10px\"\u003e\u003c\/div\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\n\n\u003cdiv style=\"width:95%\"\u003e\n\n\u003cdiv style=\"text-align:center;font-size:30px;font-weight:bolder;line-height:1.6em\"\u003e LLM in Production \u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"border-bottom:1px;border-bottom-style:dotted;border-color:;padding-bottom:20px\"\u003e\u003ccenter\u003e\u003ctable align=\"center\" width=\"100%\"\u003e\u003ctbody style=\"border:0px\"\u003e\n\n\u003ctr\u003e\u003ctd align=\"center\" style=\"line-height:1.2em;text-align:center;font-size:18px;color:black;font-weight:bold;padding-bottom:20px;\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\u003ctr\u003e\u003ctd style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/image.yes24.com\/goods\/147115595\/XL\" style=\"max-width:100%;height:auto\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/center\u003e\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;{split_style6}padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e Description \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;word-break:break-all;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eBook Introduction\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\u003cdiv\u003e \u003cb\u003eLearn how to deploy LLM-based applications to production safely and efficiently!\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e\"LLM in Production\" clearly explains, with ample examples, how practical LLMs work, how to interact with them, and how to integrate them with applications.\u003cbr\u003e This book will help you understand how LLM differs from traditional software and machine learning (ML) and provide best practices for applying LLM beyond the lab.\u003cbr\u003e The book also offers advice based on the authors' own experiences to help you avoid common problems.\u003cbr\u003e\n\n\u003c\/div\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cul\u003e\u003cli\u003e You can preview some of the book's contents.\u003cbr\u003e \u003cspan\u003ePreview\u003c\/span\u003e\n\n\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003e▣ Chapter 1: Awakening Words: Why LLMs Are Getting the Attention They deserve\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 1.1 LLM accelerates communication\u003cbr\u003e 1.2 Build your own LLM or buy it?\u003cbr\u003e __1.2.1 Purchase: The Well-Worn Path\u003cbr\u003e __1.2.2 Self-Building: The Road Less Traveled\u003cbr\u003e __1.2.3 A word of warning: Embrace the future now.\u003cbr\u003e 1.3 Breaking the superstition\u003cbr\u003e summation\u003cbr\u003e \u003cbr\u003e\u003cb\u003e▣ Chapter 2: Understanding LLM: A Deep Dive into Language Modeling\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 2.1 Language Modeling\u003cbr\u003e 2.1.1 Linguistic features\u003cbr\u003e __2.1.2 Semiotics\u003cbr\u003e __2.1.3 Multilingual NLP\u003cbr\u003e 2.2 Language modeling techniques\u003cbr\u003e __2.2.1 N-gram and corpus-based techniques\u003cbr\u003e __2.2.2 Bayesian technique\u003cbr\u003e __2.2.3 Markov chain\u003cbr\u003e __2.2.4 Continuous Language Modeling\u003cbr\u003e __2.2.5 Embedding\u003cbr\u003e __2.2.6 Multilayer Perceptron (MLP)\u003cbr\u003e __2.2.7 Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) Networks\u003cbr\u003e __2.2.8 Attention Mechanism\u003cbr\u003e 2.3 “Attention Is All You Need”\u003cbr\u003e __2.3.1 Encoder\u003cbr\u003e __2.3.2 decoder\u003cbr\u003e __2.3.3 Transformer\u003cbr\u003e 2.4 Very large transformer model\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 3: LLM Ops: Building a Platform for LLM\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 3.1 Introduction to LLM Ops\u003cbr\u003e 3.2 Challenges in running an LLM\u003cbr\u003e __3.2.1 Long download times\u003cbr\u003e __3.2.2 Longer deployment times\u003cbr\u003e __3.2.3 Delay time\u003cbr\u003e __3.2.4 GPU Management\u003cbr\u003e __3.2.5 Special characteristics of text data\u003cbr\u003e __3.2.6 Bottleneck due to token limit\u003cbr\u003e __3.2.7 Confusion due to hallucinations  \u003cbr\u003e__3.2.8 Bias and Ethical Considerations\u003cbr\u003e __3.2.9 Security Concerns\u003cbr\u003e __3.2.10 Cost Management\u003cbr\u003e 3.3 Key Elements of LLM Ops\u003cbr\u003e __3.3.1 compression\u003cbr\u003e __3.3.2 Distributed Computing\u003cbr\u003e 3.4 LLM Ops Infrastructure\u003cbr\u003e __3.4.1 Data Infrastructure\u003cbr\u003e __3.4.2 Experiment Tracker\u003cbr\u003e __3.4.3 Model Registry\u003cbr\u003e __3.4.4 Feature Repository\u003cbr\u003e __3.4.5 Vector Database\u003cbr\u003e __3.4.6 Monitoring System\u003cbr\u003e __3.4.7 GPU-enabled workstation\u003cbr\u003e __3.4.8 Distribution Service\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 4: Data Engineering for LLM: Preparing for Success\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 4.1 Model as a Foundation\u003cbr\u003e __4.1.1 GPT\u003cbr\u003e __4.1.2 BLOOM\u003cbr\u003e __4.1.3 Rama\u003cbr\u003e __4.1.4 Wizard\u003cbr\u003e __4.1.5 Falcon\u003cbr\u003e __4.1.6 Vicuna\u003cbr\u003e __4.1.7 Dolly\u003cbr\u003e __4.1.8 Open Chat\u003cbr\u003e 4.2 LLM Evaluation\u003cbr\u003e __4.2.1 Metrics for Text Evaluation\u003cbr\u003e __4.2.2 Key industry benchmarks\u003cbr\u003e __4.2.3 Responsible AI Benchmarks\u003cbr\u003e __4.2.4 Developing your own benchmark\u003cbr\u003e __4.2.5 Evaluation of the Code Generator\u003cbr\u003e __4.2.6 Model Parameter Evaluation\u003cbr\u003e 4.3 Data for LLM\u003cbr\u003e __4.3.1 Datasets to Know\u003cbr\u003e __4.3.2 Data Cleaning and Preparation  \u003cbr\u003e4.4 Text Processing\u003cbr\u003e __4.4.1 Tokenization\u003cbr\u003e __4.4.2 Embedding\u003cbr\u003e 4.5 Preparing the Slack Dataset\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 5: LLM Training: How to Create a Generator\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 5.1 Multi-GPU environment\u003cbr\u003e __5.1.1 Preferences\u003cbr\u003e __5.1.2 Library\u003cbr\u003e 5.2 Basic Training Techniques\u003cbr\u003e __5.2.1 Training from the ground up\u003cbr\u003e __5.2.2 Transfer Learning (Fine-Tuning)\u003cbr\u003e __5.2.3 Prompting\u003cbr\u003e 5.3 Advanced Training Techniques\u003cbr\u003e __5.3.1 Prompt Adjustment\u003cbr\u003e __5.3.2 Fine-tuning using knowledge distillation\u003cbr\u003e __5.3.3 RLHF (Reinforcement Learning Based on Human Feedback)\u003cbr\u003e __5.3.4 Mix of Experts (MoE)\u003cbr\u003e __5.3.5 LoRA and PEFT\u003cbr\u003e 5.4 Training Tips and Tricks\u003cbr\u003e __5.4.1 Note on Training Data Size\u003cbr\u003e __5.4.2 Efficient Training\u003cbr\u003e __5.4.3 The trap of extreme values\u003cbr\u003e __5.4.4 Hyperparameter Tuning Tips\u003cbr\u003e __5.4.5 Notes on Operating Systems\u003cbr\u003e __5.4.6 Activation Function Advice\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 6: Building an LLM Service: A Practical Guide\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 6.1 Creating an LLM Service\u003cbr\u003e __6.1.1 Compiling the model\u003cbr\u003e __6.1.2 LLM storage strategy\u003cbr\u003e __6.1.3 Adaptive Request Batching\u003cbr\u003e __6.1.4 Flow Control  \u003cbr\u003e__6.1.5 Response Streaming\u003cbr\u003e __6.1.6 Feature Repository\u003cbr\u003e __6.1.7 RAG (Research Augmentation Generation)\u003cbr\u003e __6.1.8 LLM Service Library\u003cbr\u003e 6.2 Infrastructure Construction\u003cbr\u003e __6.2.1 Cluster Preparation\u003cbr\u003e __6.2.2 Auto-expansion\u003cbr\u003e __6.2.3 Rolling Update\u003cbr\u003e __6.2.4 Inference Graph\u003cbr\u003e __6.2.5 Monitoring\u003cbr\u003e 6.3 Production Challenges\u003cbr\u003e __6.3.1 Model Update and Retraining\u003cbr\u003e __6.3.2 Load Testing\u003cbr\u003e __6.3.3 Troubleshooting Latency Issues\u003cbr\u003e __6.3.4 Resource Management\u003cbr\u003e __6.3.5 Cost Engineering\u003cbr\u003e __6.3.6 Security\u003cbr\u003e 6.4 Edge Deployment\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 7: Prompt Engineering: Becoming an LLM Trainer\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 7.1 Model Prompting\u003cbr\u003e __7.1.1 Few-shot prompting\u003cbr\u003e __7.1.2 One-shot prompting\u003cbr\u003e __7.1.3 Zero-shot prompting\u003cbr\u003e 7.2 Fundamentals of Prompt Engineering\u003cbr\u003e __7.2.1 Anatomy of a Prompt\u003cbr\u003e __7.2.2 Prompt hyperparameters\u003cbr\u003e __7.2.3 Examining the Training Data\u003cbr\u003e 7.3 Prompt Engineering Tools\u003cbr\u003e __7.3.1 Langchain\u003cbr\u003e __7.3.2 Guidance\u003cbr\u003e __7.3.3 DSPy\u003cbr\u003e __7.3.4 There are other tools too…\u003cbr\u003e 7.4 Advanced Prompt Engineering Techniques  \u003cbr\u003e__7.4.1 Providing Tools for LLM\u003cbr\u003e __7.4.2 ReAct\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 8: LLM Applications: Building Interactive Experiences\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 8.1 Creating an Application\u003cbr\u003e __8.1.1 Streaming on the Front End\u003cbr\u003e __8.1.2 Maintain conversation history\u003cbr\u003e __8.1.3 Chatbot Interaction Features\u003cbr\u003e __8.1.4 Token Counter\u003cbr\u003e __8.1.5 RAG application\u003cbr\u003e 8.2 Edge Applications\u003cbr\u003e 8.3 LLM Agent\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 9: Creating an LLM Project: Reimplementing Rama3\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 9.1 Meta's Llama Reimplementation\u003cbr\u003e __9.1.1 Tokenization and Settings\u003cbr\u003e __9.1.2 Preparing the dataset, loading data, evaluating it, and creating it\u003cbr\u003e __9.1.3 Model Architecture\u003cbr\u003e 9.2 Simplified Rama3\u003cbr\u003e 9.3 Model Improvements\u003cbr\u003e __9.3.1 Quantization\u003cbr\u003e __9.3.2 LoRA\u003cbr\u003e __9.3.3 FSDP QLoRA Application\u003cbr\u003e 9.4 Deploying the Model to the Hugging Face Space\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 10: Creating a Coding Copilot Project: Will It Actually Help?\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 10.1 Example Model\u003cbr\u003e 10.2 Data is king\u003cbr\u003e __10.2.1 Example Vector DB\u003cbr\u003e __10.2.2 Example Dataset\u003cbr\u003e __10.2.3 RAG application\u003cbr\u003e 10.3 Creating a VS Code Extension  \u003cbr\u003e10.4 Lessons Learned and Next Steps\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 11: Deploying LLM on a Raspberry Pi: How small can you make it?\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 11.1 Setting up the Raspberry Pi\u003cbr\u003e __11.1.1 Preparing OS images using Pie Imager\u003cbr\u003e __11.1.2 Connecting to the Pi\u003cbr\u003e __11.1.3 Software Installation and Update\u003cbr\u003e 11.2 Preparing the Model\u003cbr\u003e 11.3 Model Serving\u003cbr\u003e 11.4 Improvements\u003cbr\u003e __11.4.1 Better interface\u003cbr\u003e __11.4.2 Quantization changes\u003cbr\u003e __11.4.3 Adding multiple modals\u003cbr\u003e __11.4.4 Serving Models in Google Colab\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 12: Production, a constantly changing landscape: This is just the beginning.\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 12.1 Overall view\u003cbr\u003e 12.2 The Future of LLM\u003cbr\u003e __12.2.1 Government and Regulation\u003cbr\u003e __12.2.2 LLM continues to grow\u003cbr\u003e __12.2.3 Multimodal Space\u003cbr\u003e __12.2.4 dataset\u003cbr\u003e __12.2.5 Solving the hallucination problem\u003cbr\u003e __12.2.6 New hardware\u003cbr\u003e __12.2.7 The usefulness of the agent will be proven.\u003cbr\u003e 12.3 Concluding remarks\u003cbr\u003e summation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix A: A Brief History of Linguistics\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e A.1 Ancient Linguistics\u003cbr\u003e A.2 Medieval Linguistics  \u003cbr\u003eA.3 Renaissance and Modern Linguistics\u003cbr\u003e A.4 Early 20th Century Linguistics\u003cbr\u003e A.5 Mid-20th Century and Modern Linguistics\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix B: RLHF (Reinforcement Learning Based on Human Feedback)\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix C: Multimodal Latent Space\u003c\/b\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eDetailed image\u003c\/b\u003e \u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cimg src=\"https:\/\/image.yes24.com\/momo\/TopCate5347\/MidCate007\/534660910.jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003ePublisher's Review\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003e★ What this book covers ★\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e ◎ Basic concepts and foundational technologies of LLM\u003cbr\u003e ◎ How to evaluate whether to use a pre-trained LLM or build your own\u003cbr\u003e ◎ How to efficiently scale the ML platform to handle LLM requirements\u003cbr\u003e ◎ How to train the foundation model of LLM and fine-tune the existing LLM\u003cbr\u003e ◎ How to deploy LLM to cloud and edge devices by leveraging complex architectures such as PEFT and LoRA.\u003cbr\u003e ◎ How to build an application that maximizes the strengths of LLM while compensating for its weaknesses\u003cbr\u003e \u003cbr\u003e\"LLM in Production\" provides essential insights for seamlessly deploying LLMs into production using MLops. It provides practical guidance, from securing datasets suitable for LLM training to building platforms and addressing challenges associated with large model sizes.\u003cbr\u003e We also cover practical tips and techniques for prompt engineering, model retraining, load testing, cost management, and security hardening. \u003cbr\u003e\n\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e GOODS SPECIFICS \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eDate of issue:\u003c\/strong\u003e June 18, 2025\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003ePage count, weight, size:\u003c\/strong\u003e 556 pages | 188*240*23mm\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN13:\u003c\/strong\u003e 9791158396091\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN10:\u003c\/strong\u003e 1158396090 \u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cspan\u003e\u003c\/span\u003e\n\n\u003c\/center\u003e\n\n\n\u003c\/center\u003e","brand":"LIBRAIRIE COREENNE","offers":[{"title":"Default Title","offer_id":43893235875882,"sku":"138387","price":44.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/1e6bbb861e7428ca2bc3c206895794c3.jpg?v=1765393193","url":"https:\/\/librairie.coreenne.fr\/en\/products\/138387","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}