Wu fuheng (40 resultados)

Paperback or Softback. Condición: New. Distributed AI Systems: A practical guide to building scalable training, inference, and serving systems for production AI. Book.

Condición: New.

Condición: New.

Paperback. Condición: New. Learn distributed AI through hands-on experience with training frameworks, inference engines, and orchestration tools to build production-ready training, inference, and serving systems for modern large-scale AI. Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand GPU hardware, high-speed interconnects, and parallelism strategiesHands-on exercises at the end of every chapterLearn distributed training with resource-optimized techniquesDeploy high-performance inference with advanced optimization and memory managementBuild production serving stacks with job schedulers, orchestration, and observabilityBook DescriptionAs AI models grow to billions and trillions of parameters, distributed systems are essential for training and serving them. Many resources cover fragments of this domain, but none provide a full path from distributed training to inference and production deployment. This book fills that gap with practical, production-focused examples.It starts with GPU and memory estimation, data preparation, and an overview of GPU architecture, interconnects, and core parallelism strategies. You'll learn training techniques including data parallelism for single and multi-node setups, parameter sharding for memory-efficient scaling, and methods to reduce memory usage in large models.The next section covers distributed inference and deployment. You'll build high-performance systems using optimized attention, caching, operator fusion, and router-based designs. You'll deploy on schedulers and container platforms with GPU-aware orchestration and assemble production stacks emphasizing reliability, scalability, and observability.The final section covers benchmarking, performance tuning, and trends like MoE models, edge-cloud coordination, and advanced parallelism. Each chapter includes tested code and debugging guidance.By the end, you'll be able to build distributed AI systems that scale from a single GPU to large clusters.What you will learnEstimate memory and compute requirements for training and inferenceUnderstand GPU hardware, interconnects, and parallelism strategiesImplement distributed training with parallel and sharded techniquesBuild production inference systems with batching and memory managementDeploy via cluster orchestration with optimized GPU schedulingCreate production serving stacks with routing and observabilityBenchmark distributed systems using industry-standard methodologiesExplore emerging model trends, scaling strategies, and future pathsWho this book is forThis book is designed for ML engineers, AI researchers, and DevOps professionals who need to train or serve large AI models at scale. Platform engineers, HPC cluster administrators, and cloud architects will also find it valuable for advancing their skill sets.A basic understanding of Python and PyTorch is required to get started. Prior experience with distributed systems, cluster schedulers, or container orchestration is helpful but not.…

Condición: New.

Condición: New.

Condición: New.

Condición: New.

Paperback. Condición: New. Learn distributed AI through hands-on experience with training frameworks, inference engines, and orchestration tools to build production-ready training, inference, and serving systems for modern large-scale AI. Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand GPU hardware, high-speed interconnects, and parallelism strategiesHands-on exercises at the end of every chapterLearn distributed training with resource-optimized techniquesDeploy high-performance inference with advanced optimization and memory managementBuild production serving stacks with job schedulers, orchestration, and observabilityBook DescriptionAs AI models grow to billions and trillions of parameters, distributed systems are essential for training and serving them. Many resources cover fragments of this domain, but none provide a full path from distributed training to inference and production deployment. This book fills that gap with practical, production-focused examples.It starts with GPU and memory estimation, data preparation, and an overview of GPU architecture, interconnects, and core parallelism strategies. You'll learn training techniques including data parallelism for single and multi-node setups, parameter sharding for memory-efficient scaling, and methods to reduce memory usage in large models.The next section covers distributed inference and deployment. You'll build high-performance systems using optimized attention, caching, operator fusion, and router-based designs. You'll deploy on schedulers and container platforms with GPU-aware orchestration and assemble production stacks emphasizing reliability, scalability, and observability.The final section covers benchmarking, performance tuning, and trends like MoE models, edge-cloud coordination, and advanced parallelism. Each chapter includes tested code and debugging guidance.By the end, you'll be able to build distributed AI systems that scale from a single GPU to large clusters.What you will learnEstimate memory and compute requirements for training and inferenceUnderstand GPU hardware, interconnects, and parallelism strategiesImplement distributed training with parallel and sharded techniquesBuild production inference systems with batching and memory managementDeploy via cluster orchestration with optimized GPU schedulingCreate production serving stacks with routing and observabilityBenchmark distributed systems using industry-standard methodologiesExplore emerging model trends, scaling strategies, and future pathsWho this book is forThis book is designed for ML engineers, AI researchers, and DevOps professionals who need to train or serve large AI models at scale. Platform engineers, HPC cluster administrators, and cloud architects will also find it valuable for advancing their skill sets.A basic understanding of Python and PyTorch is required to get started. Prior experience with distributed systems, cluster schedulers, or container orchestration is helpful but not.…

Paperback. Condición: new. Paperback. A coding agent looks like a language model with a code prompt. It isn't. An LLM emits probabilistic tokens; an autonomous coding agent navigates unfamiliar codebases, formulates hypotheses, executes shell commands, inspects compiler diagnostics, and repairs multi-file regressions under strict token, latency, and financial budgets. The moment a model interacts with a filesystem and a shell, the primary engineering challenge ceases to be prompt engineering. It becomes software systems engineering.This book is an architectural and production guide to engineering systems in which humans and coding agents work reliably together on real codebases. It treats coding agents not as chatbots, but as composite software engineering systems built around foundation models. Every chapter bridges theoretical mechanics with concrete architectural blueprints: how context allocators manage active working sets, how tool dispatchers enforce secure capability boundaries, how isolated sandboxes execute mutations, and how closed-loop verification pipelines transform raw model proposals into verified pull requests.The early chapters establish the foundational mechanics and core architecture: Code LLM token economics, KV cache utilization, deterministic execution theory, and prompt/harness boundary contracts. It then dissects the 7-component agent stack: tool calling protocols, structured orchestrator loops, memory layers, and multi-agent coordination topologies (hierarchical supervisors, peer pipelines, and collaborative swarms).The later chapters focus on verification, harnesses, and production scale: why ungrounded agents hallucinate syntactically plausible regressions, how to build robust generate-verify-repair loops with AST linters and test runners, and how SWE-bench evaluation prevents contamination. The concluding chapters deliver enterprise engineering practices: microVM and gVisor container sandboxing, CI/CD integration gates, permission deny-lists, cost controls, and self-improving agents that distill lessons from repository execution traces.For software engineers, ML system architects, developer tooling engineers, and engineering leaders building the next generation of AI-augmented software workflows. The code examples are standalone, all architectures verified against production benchmarks, and each chapter closes with technical exercises and architectural checklists. An architectural and production guide to engineering autonomous coding agents. Covers agent stack, context allocation, tool calling protocols, test-driven verification harnesses, evaluation, sandboxing, and enterprise workflows. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

Paperback. Condición: new. Paperback. Learn distributed AI through hands-on experience with training frameworks, inference engines, and orchestration tools to build production-ready training, inference, and serving systems for modern large-scale AI.Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand GPU hardware, high-speed interconnects, and parallelism strategiesHands-on exercises at the end of every chapterLearn distributed training with resource-optimized techniquesDeploy high-performance inference with advanced optimization and memory managementBuild production serving stacks with job schedulers, orchestration, and observabilityBook DescriptionAs AI models grow to billions and trillions of parameters, distributed systems are essential for training and serving them. Many resources cover fragments of this domain, but none provide a full path from distributed training to inference and production deployment. This book fills that gap with practical, production-focused examples.It starts with GPU and memory estimation, data preparation, and an overview of GPU architecture, interconnects, and core parallelism strategies. Youll learn training techniques including data parallelism for single and multi-node setups, parameter sharding for memory-efficient scaling, and methods to reduce memory usage in large models.The next section covers distributed inference and deployment. Youll build high-performance systems using optimized attention, caching, operator fusion, and router-based designs. Youll deploy on schedulers and container platforms with GPU-aware orchestration and assemble production stacks emphasizing reliability, scalability, and observability.The final section covers benchmarking, performance tuning, and trends like MoE models, edge-cloud coordination, and advanced parallelism. Each chapter includes tested code and debugging guidance.By the end, youll be able to build distributed AI systems that scale from a single GPU to large clusters.What you will learnEstimate memory and compute requirements for training and inferenceUnderstand GPU hardware, interconnects, and parallelism strategiesImplement distributed training with parallel and sharded techniquesBuild production inference systems with batching and memory managementDeploy via cluster orchestration with optimized GPU schedulingCreate production serving stacks with routing and observabilityBenchmark distributed systems using industry-standard methodologiesExplore emerging model trends, scaling strategies, and future pathsWho this book is forThis book is designed for ML engineers, AI researchers, and DevOps professionals who need to train or serve large AI models at scale. Platform engineers, HPC cluster administrators, and cloud architects will also find it valuable for advancing their skill sets.A basic understanding of Python and PyTorch is required to get started. Prior experience with distributed systems, cluster schedulers, or container orchestration is helpful but not necessary - the book introduces these concepts from the ground up, beginning with resource estimation, data preparation, and hardware fundamentals. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

Paperback. Condición: new. Paperback. This book explains the US mortgage market in plain language first, then the mathematics, then the AI now taking over the work. It follows eight people through the life of one loan - Jack the borrower, Maya the loan officer, Priya the servicer, Benny the dealer, Elena the investor, Peter the quant, Melissa the examiner, and Simon the retail saver - and every formula arrives attached to whoever uses it.Nine chapters carry one thirty-year payment stream from a kitchen table to a trading desk. The early chapters build the mortgage: amortization, underwriting and credit, pooling, the prepayment conventions (SMM, CPR, PSA), and why the 2007 loans defaulted together. The middle chapters add the desk's machinery: SOFR discounting, DV01 and key rate durations, Ito's lemma and short-rate models, the prepayment option as a receiver swaption, and option-adjusted spread.Machine learning runs alongside from the first chapter: each chapter before the last ends its theory with a bridge from the classical method to the learned one, from loan-level feature vectors and survival networks to neural SDEs. The last chapter puts it to work where it pays - hybrid models that keep an explainable baseline and learn only the residual, neural pricing surrogates that compute OAS and DV01 in real time, GPU numerics - and covers the governance a model validator will demand before any of it runs with money behind it.Every chapter ends with a retail window, because agency MBS is probably already in your bond fund. Key results are measured on Fannie Mae's loan-level data, and every function the book names is in mortgagekit, its open-source Python companion. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. …

PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000.

Condición: New. Print on Demand.

Hardcover. Condición: new. Hardcover. AIFuheng Wu-Singapore-MIT Alliance- AI ""-"" This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.

Paperback. Condición: new. Paperback. Learn distributed AI through hands-on experience with training frameworks, inference engines, and orchestration tools to build production-ready training, inference, and serving systems for modern large-scale AI.Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand GPU hardware, high-speed interconnects, and parallelism strategiesHands-on exercises at the end of every chapterLearn distributed training with resource-optimized techniquesDeploy high-performance inference with advanced optimization and memory managementBuild production serving stacks with job schedulers, orchestration, and observabilityBook DescriptionAs AI models grow to billions and trillions of parameters, distributed systems are essential for training and serving them. Many resources cover fragments of this domain, but none provide a full path from distributed training to inference and production deployment. This book fills that gap with practical, production-focused examples.It starts with GPU and memory estimation, data preparation, and an overview of GPU architecture, interconnects, and core parallelism strategies. Youll learn training techniques including data parallelism for single and multi-node setups, parameter sharding for memory-efficient scaling, and methods to reduce memory usage in large models.The next section covers distributed inference and deployment. Youll build high-performance systems using optimized attention, caching, operator fusion, and router-based designs. Youll deploy on schedulers and container platforms with GPU-aware orchestration and assemble production stacks emphasizing reliability, scalability, and observability.The final section covers benchmarking, performance tuning, and trends like MoE models, edge-cloud coordination, and advanced parallelism. Each chapter includes tested code and debugging guidance.By the end, youll be able to build distributed AI systems that scale from a single GPU to large clusters.What you will learnEstimate memory and compute requirements for training and inferenceUnderstand GPU hardware, interconnects, and parallelism strategiesImplement distributed training with parallel and sharded techniquesBuild production inference systems with batching and memory managementDeploy via cluster orchestration with optimized GPU schedulingCreate production serving stacks with routing and observabilityBenchmark distributed systems using industry-standard methodologiesExplore emerging model trends, scaling strategies, and future pathsWho this book is forThis book is designed for ML engineers, AI researchers, and DevOps professionals who need to train or serve large AI models at scale. Platform engineers, HPC cluster administrators, and cloud architects will also find it valuable for advancing their skill sets.A basic understanding of Python and PyTorch is required to get started. Prior experience with distributed systems, cluster schedulers, or container orchestration is helpful but not necessary - the book introduces these concepts from the ground up, beginning with resource estimation, data preparation, and hardware fundamentals. This item is printed on demand. Shipping may be from our Sydney, NSW warehouse or from our UK or US warehouse, depending on stock availability.…

Condición: New. PRINT ON DEMAND.

Paperback. Condición: new. Paperback. A coding agent looks like a language model with a code prompt. It isn't. An LLM emits probabilistic tokens; an autonomous coding agent navigates unfamiliar codebases, formulates hypotheses, executes shell commands, inspects compiler diagnostics, and repairs multi-file regressions under strict token, latency, and financial budgets. The moment a model interacts with a filesystem and a shell, the primary engineering challenge ceases to be prompt engineering. It becomes software systems engineering.This book is an architectural and production guide to engineering systems in which humans and coding agents work reliably together on real codebases. It treats coding agents not as chatbots, but as composite software engineering systems built around foundation models. Every chapter bridges theoretical mechanics with concrete architectural blueprints: how context allocators manage active working sets, how tool dispatchers enforce secure capability boundaries, how isolated sandboxes execute mutations, and how closed-loop verification pipelines transform raw model proposals into verified pull requests.The early chapters establish the foundational mechanics and core architecture: Code LLM token economics, KV cache utilization, deterministic execution theory, and prompt/harness boundary contracts. It then dissects the 7-component agent stack: tool calling protocols, structured orchestrator loops, memory layers, and multi-agent coordination topologies (hierarchical supervisors, peer pipelines, and collaborative swarms).The later chapters focus on verification, harnesses, and production scale: why ungrounded agents hallucinate syntactically plausible regressions, how to build robust generate-verify-repair loops with AST linters and test runners, and how SWE-bench evaluation prevents contamination. The concluding chapters deliver enterprise engineering practices: microVM and gVisor container sandboxing, CI/CD integration gates, permission deny-lists, cost controls, and self-improving agents that distill lessons from repository execution traces.For software engineers, ML system architects, developer tooling engineers, and engineering leaders building the next generation of AI-augmented software workflows. The code examples are standalone, all architectures verified against production benchmarks, and each chapter closes with technical exercises and architectural checklists. An architectural and production guide to engineering autonomous coding agents. Covers agent stack, context allocation, tool calling protocols, test-driven verification harnesses, evaluation, sandboxing, and enterprise workflows. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. A mortgage looks like the simplest contract in finance: someone borrows against a house and pays it back monthly. It isn't. The borrower can repay early at any time - because rates fell, because a job moved, because a marriage ended - and that one option is why a mortgage is not a bond, why it can lose value whether rates rise or fall, and why an industry exists to forecast when one borrower refinances.This book explains the US mortgage market in plain language first, then the mathematics. It follows five people through the life of one loan: Jack the borrower, Maya the loan officer, Priya the servicer, Ben the dealer, and Elena the investor. Every formula arrives attached to whoever uses it, and all of it ties back to one object: a thirty-year payment stream.Nine chapters carry that stream from a kitchen table to a trading desk. The early chapters build the mortgage itself: amortization, underwriting, pooling, and the prepayment conventions (SMM, CPR, PSA) that describe how fast a pool pays down. The middle chapters add the machinery a desk runs on: SOFR discounting, DV01, CV01, and key rate durations; Ito's lemma applied to the Vasicek and Hull-White short-rate models; the prepayment option as a receiver swaption on the mortgage rate; and option-adjusted spread as pricing by expected discounted payoff.The final chapters are about what breaks: why prepayment forecasting sits at the center of pricing, servicing, and hedging, and how millions of loans collapse into priceable cohorts; why a hedge that is right at 9:30 is wrong by 9:31, why no traded instrument shares Jack's psychology, and how every desk hedging convexity the same way turns a small rate move into a large one. The last chapter brings the modern toolkit - hybrid ensembles, competing-risk survival trees, neural SDEs for joint rate and home-price paths, neural pricing surrogates for real-time OAS - plus the governance that makes it safe to run with money behind it.For analysts, investors, quantitative developers, and practitioners. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. Learn distributed AI through hands-on experience with training frameworks, inference engines, and orchestration tools to build production-ready training, inference, and serving systems for modern large-scale AI.Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand GPU hardware, high-speed interconnects, and parallelism strategiesHands-on exercises at the end of every chapterLearn distributed training with resource-optimized techniquesDeploy high-performance inference with advanced optimization and memory managementBuild production serving stacks with job schedulers, orchestration, and observabilityBook DescriptionAs AI models grow to billions and trillions of parameters, distributed systems are essential for training and serving them. Many resources cover fragments of this domain, but none provide a full path from distributed training to inference and production deployment. This book fills that gap with practical, production-focused examples.It starts with GPU and memory estimation, data preparation, and an overview of GPU architecture, interconnects, and core parallelism strategies. Youll learn training techniques including data parallelism for single and multi-node setups, parameter sharding for memory-efficient scaling, and methods to reduce memory usage in large models.The next section covers distributed inference and deployment. Youll build high-performance systems using optimized attention, caching, operator fusion, and router-based designs. Youll deploy on schedulers and container platforms with GPU-aware orchestration and assemble production stacks emphasizing reliability, scalability, and observability.The final section covers benchmarking, performance tuning, and trends like MoE models, edge-cloud coordination, and advanced parallelism. Each chapter includes tested code and debugging guidance.By the end, youll be able to build distributed AI systems that scale from a single GPU to large clusters.What you will learnEstimate memory and compute requirements for training and inferenceUnderstand GPU hardware, interconnects, and parallelism strategiesImplement distributed training with parallel and sharded techniquesBuild production inference systems with batching and memory managementDeploy via cluster orchestration with optimized GPU schedulingCreate production serving stacks with routing and observabilityBenchmark distributed systems using industry-standard methodologiesExplore emerging model trends, scaling strategies, and future pathsWho this book is forThis book is designed for ML engineers, AI researchers, and DevOps professionals who need to train or serve large AI models at scale. Platform engineers, HPC cluster administrators, and cloud architects will also find it valuable for advancing their skill sets.A basic understanding of Python and PyTorch is required to get started. Prior experience with distributed systems, cluster schedulers, or container orchestration is helpful but not necessary - the book introduces these concepts from the ground up, beginning with resource estimation, data preparation, and hardware fundamentals. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condición: new. Paperback. A coding agent looks like a language model with a code prompt. It isn't. An LLM emits probabilistic tokens; an autonomous coding agent navigates unfamiliar codebases, formulates hypotheses, executes shell commands, inspects compiler diagnostics, and repairs multi-file regressions under strict token, latency, and financial budgets. The moment a model interacts with a filesystem and a shell, the primary engineering challenge ceases to be prompt engineering. It becomes software systems engineering.This book is an architectural and production guide to engineering systems in which humans and coding agents work reliably together on real codebases. It treats coding agents not as chatbots, but as composite software engineering systems built around foundation models. Every chapter bridges theoretical mechanics with concrete architectural blueprints: how context allocators manage active working sets, how tool dispatchers enforce secure capability boundaries, how isolated sandboxes execute mutations, and how closed-loop verification pipelines transform raw model proposals into verified pull requests.The early chapters establish the foundational mechanics and core architecture: Code LLM token economics, KV cache utilization, deterministic execution theory, and prompt/harness boundary contracts. It then dissects the 7-component agent stack: tool calling protocols, structured orchestrator loops, memory layers, and multi-agent coordination topologies (hierarchical supervisors, peer pipelines, and collaborative swarms).The later chapters focus on verification, harnesses, and production scale: why ungrounded agents hallucinate syntactically plausible regressions, how to build robust generate-verify-repair loops with AST linters and test runners, and how SWE-bench evaluation prevents contamination. The concluding chapters deliver enterprise engineering practices: microVM and gVisor container sandboxing, CI/CD integration gates, permission deny-lists, cost controls, and self-improving agents that distill lessons from repository execution traces.For software engineers, ML system architects, developer tooling engineers, and engineering leaders building the next generation of AI-augmented software workflows. The code examples are standalone, all architectures verified against production benchmarks, and each chapter closes with technical exercises and architectural checklists. An architectural and production guide to engineering autonomous coding agents. Covers agent stack, context allocation, tool calling protocols, test-driven verification harnesses, evaluation, sandboxing, and enterprise workflows. This item is printed on demand. Shipping may be from our Sydney, NSW warehouse or from our UK or US warehouse, depending on stock availability.…

Paperback. Condición: new. Paperback. A mortgage looks like the simplest contract in finance: someone borrows against a house and pays it back monthly. It isn't. The borrower can repay early at any time - because rates fell, because a job moved, because a marriage ended - and that one option is why a mortgage is not a bond, why it can lose value whether rates rise or fall, and why an industry exists to forecast when one borrower refinances.This book explains the US mortgage market in plain language first, then the mathematics. It follows five people through the life of one loan: Jack the borrower, Maya the loan officer, Priya the servicer, Ben the dealer, and Elena the investor. Every formula arrives attached to whoever uses it, and all of it ties back to one object: a thirty-year payment stream.Nine chapters carry that stream from a kitchen table to a trading desk. The early chapters build the mortgage itself: amortization, underwriting, pooling, and the prepayment conventions (SMM, CPR, PSA) that describe how fast a pool pays down. The middle chapters add the machinery a desk runs on: SOFR discounting, DV01, CV01, and key rate durations; Ito's lemma applied to the Vasicek and Hull-White short-rate models; the prepayment option as a receiver swaption on the mortgage rate; and option-adjusted spread as pricing by expected discounted payoff.The final chapters are about what breaks: why prepayment forecasting sits at the center of pricing, servicing, and hedging, and how millions of loans collapse into priceable cohorts; why a hedge that is right at 9:30 is wrong by 9:31, why no traded instrument shares Jack's psychology, and how every desk hedging convexity the same way turns a small rate move into a large one. The last chapter brings the modern toolkit - hybrid ensembles, competing-risk survival trees, neural SDEs for joint rate and home-price paths, neural pricing surrogates for real-time OAS - plus the governance that makes it safe to run with money behind it.For analysts, investors, quantitative developers, and practitioners. This item is printed on demand. Shipping may be from our Sydney, NSW warehouse or from our UK or US warehouse, depending on stock availability.…

Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - A coding agent looks like a language model with a code prompt. It isn't. An LLM emits probabilistic tokens; an autonomous coding agent navigates unfamiliar codebases, formulates hypotheses, executes shell commands, inspects compiler diagnostics, and repairs multi-file regressions under strict token, latency, and financial budgets. The moment a model interacts with a filesystem and a shell, the primary engineering challenge ceases to be prompt engineering. It becomes software systems engineering.This book is an architectural and production guide to engineering systems in which humans and coding agents work reliably together on real codebases. It treats coding agents not as chatbots, but as composite software engineering systems built around foundation models. Every chapter bridges theoretical mechanics with concrete architectural blueprints: how context allocators manage active working sets, how tool dispatchers enforce secure capability boundaries, how isolated sandboxes execute mutations, and how closed-loop verification pipelines transform raw model proposals into verified pull requests.The early chapters establish the foundational mechanics and core architecture: Code LLM token economics, KV cache utilization, deterministic execution theory, and prompt/harness boundary contracts. It then dissects the 7-component agent stack: tool calling protocols, structured orchestrator loops, memory layers, and multi-agent coordination topologies (hierarchical supervisors, peer pipelines, and collaborative swarms).The later chapters focus on verification, harnesses, and production scale: why ungrounded agents hallucinate syntactically plausible regressions, how to build robust generate-verify-repair loops with AST linters and test runners, and how SWE-bench evaluation prevents contamination. The concluding chapters deliver enterprise engineering practices: microVM and gVisor container sandboxing, CI/CD integration gates, permission deny-lists, cost controls, and self-improving agents that distill lessons from repository execution traces.For software engineers, ML system architects, developer tooling engineers, and engineering leaders building the next generation of AI-augmented software workflows. The code examples are standalone, all architectures verified against production benchmarks, and each chapter closes with technical exercises and architectural checklists.…

Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - This book explains the US mortgage market in plain language first, then the mathematics, then the AI now taking over the work. It follows eight people through the life of one loan - Jack the borrower, Maya the loan officer, Priya the servicer, Benny the dealer, Elena the investor, Peter the quant, Melissa the examiner, and Simon the retail saver - and every formula arrives attached to whoever uses it.Nine chapters carry one thirty-year payment stream from a kitchen table to a trading desk. The early chapters build the mortgage: amortization, underwriting and credit, pooling, the prepayment conventions (SMM, CPR, PSA), and why the 2007 loans defaulted together. The middle chapters add the desk's machinery: SOFR discounting, DV01 and key rate durations, Itô's lemma and short-rate models, the prepayment option as a receiver swaption, and option-adjusted spread.Machine learning runs alongside from the first chapter: each chapter before the last ends its theory with a bridge from the classical method to the learned one, from loan-level feature vectors and survival networks to neural SDEs. The last chapter puts it to work where it pays - hybrid models that keep an explainable baseline and learn only the residual, neural pricing surrogates that compute OAS and DV01 in real time, GPU numerics - and covers the governance a model validator will demand before any of it runs with money behind it.Every chapter ends with a retail window, because agency MBS is probably already in your bond fund. Key results are measured on Fannie Mae's loan-level data, and every function the book names is in mortgagekit, its open-source Python companion.…

Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering.