15,762 technical terms and definitions
model parallelism communication overhead and synchronization, model parallelism communication, parallelism communication overhead, communication overhead synchronization, model parallelism
Model Parallelism Communication Overhead and Synchronization Introduction & Motivation Model Parallelism Communication Overhead and Synchronization addresses a central problem…
model parallelism layer distribution and device placement, model parallelism layer, parallelism layer distribution, layer distribution device, distribution device placement
Model Parallelism Layer Distribution and Device Placement Introduction & Motivation Model Parallelism Layer Distribution and Device Placement addresses a central problem…
distributed training
Model parallelism strategies split large neural networks across multiple GPUs when a model doesn't fit in single GPU memory, enabling training and inference of models…
distributed model training, tensor parallelism model, pipeline parallelism training, 3d parallelism
Model Parallelism Strategies are the techniques for distributing a single neural network across multiple GPUs or nodes when the model is too large to fit on a single device…
mpc, control theory
Model Predictive Control (MPC) is an advanced control strategy that uses a mathematical model of the system to predict future behavior — and solves an optimization problem at each…
manufacturing operations
Model Predictive Control is an optimization-based control strategy that computes future control moves over a prediction horizon - It is a core method in modern semiconductor…
Model Predictive Control for RL Introduction & Motivation Model Predictive Control for RL addresses a central problem in sequential decision making via deeprl: how to Learn…
Model Predictive Control for RL (Extended Study) Introduction & Motivation Model Predictive Control for RL (Extended Study) addresses a central problem in sequential decision…
Model Predictive Control for RL (Extended Study) Introduction & Motivation Model Predictive Control for RL (Extended Study) addresses a central problem in sequential decision…
process control
MPC (Model Predictive Control) in semiconductor manufacturing is a multi-variable control strategy that uses a process model to predict future outputs and optimize control actions…
model predictive control mpc, model predictive control, predictive control mpc, model predictive, predictive control, control mpc
Model Predictive Control MPC Introduction & Motivation Model Predictive Control MPC addresses a central problem in robotics process control and predictive-model-future-trajectory…
model predictive control (mpc) prediction, model predictive control, predictive control (mpc), control (mpc) prediction, model predictive, predictive control, control (mpc)
Model Predictive Control (MPC) Prediction with Machine Learning Introduction & Motivation Model Predictive Control (MPC) Prediction with Machine Learning addresses a central…
Model Predictive Path Integral MPPI Control Introduction & Motivation Model Predictive Path Integral MPPI Control addresses a central problem in reinforcement policy learning…
structured pruning, channel pruning, filter pruning, network slimming
Network slimming is a structured pruning technique that uses the learned scaling factors in batch normalization layers as the importance criterion for deciding which channels…
weight pruning neural network, lottery ticket hypothesis, magnitude pruning, sparse neural network
Unstructured weight pruning, most notably explored through the lottery ticket hypothesis's iterative magnitude pruning procedure, removes individual weights rather than whole…
structured unstructured pruning, magnitude pruning lottery ticket, pruning neural network compression, iterative pruning fine tuning
Model pruning for weight sparsity brings together several complementary techniques into a complete toolkit: structured versus unstructured pruning as the fundamental choice…
model quantization accuracy loss prediction, model quantization accuracy, quantization accuracy loss, accuracy loss prediction, model quantization, quantization accuracy
Model Quantization Accuracy Loss Prediction with Machine Learning Introduction & Motivation Model Quantization Accuracy Loss Prediction with Machine Learning addresses a central…
quantization, post training quantization, ptq, qat, gptq, awq, smoothquant, int8, int4
Model quantization reduces the numerical precision used to store or compute neural-network weights and activations. Moving FP32 models to FP16, BF16, FP8, INT8, INT4, or mixed…
weight quantization llm, int8 int4 quantization, gptq awq quantization, quantization aware training
Model Quantization is the inference optimization technique that reduces the numerical precision of neural network weights and activations from 32-bit or 16-bit floating-point…
int8 int4 quantization, gptq awq quantization, weight quantization llm, post training quantization
Model Quantization is the compression technique that reduces neural network weight and activation precision from 32-bit or 16-bit floating point to lower bit-widths (INT8, INT4…
post training quantization, quantization aware training, quantization calibration range, weight activation quantization
Model Quantization is the neural network compression technique that converts floating-point weights and activations to lower-precision integer representations (INT8, INT4…
post training quantization ptq, quantization aware training qat, int8 int4 quantization, weight activation quantization
Model Quantization is the compression technique that reduces neural network weight and activation precision from 32-bit floating-point to lower-bitwidth representations (INT8…
ml model registry, model versioning, mlflow registry, wandb artifacts, sagemaker model registry, vertex ai registry
Model registry is an authoritative catalog of versioned model artifacts, metadata, lineage, approvals and deployment status. It turns an opaque checkpoint file into a governed…
mlops
A model registry is a central repository for storing, versioning, and managing trained machine learning models. Core features: Versioning: Track model versions with metadata.…
model registry and management, model registry management, model registry, registry management
Model Registry and Management Introduction & Motivation Model Registry and Management addresses a central problem in ml-ops process control and registry-query-latency prediction…
mlops
Model retraining periodically updates model weights on fresh data to maintain performance as distributions shift. Why retrain: Combat data drift and concept drift, incorporate new…
model robustness and adversarial training, model robustness adversarial, robustness adversarial training, model robustness, robustness adversarial, adversarial training
Model Robustness and Adversarial Training Introduction & Motivation Model Robustness and Adversarial Training addresses a central problem in ml-robustness process control…
optimization
Model Routing is decision logic that selects the most suitable model for each request based on intent and constraints - It is a core method in modern semiconductor AI serving…
serving, runtime
Model serving infrastructure hosts machine learning models for inference, handling request batching, scaling, API management, and optimization to deliver low-latency predictions…
inference serving, vllm, tgi, tensorrt llm, triton inference server
model serving is the production infrastructure that turns trained models into reliable low-latency prediction services. Serving determines accelerator utilization, tail latency…
model serving, deployment tensorflow serving, api cpu gpu ml onnx passed, model serving & deployment tensorflow serving onnx & production, model serving deployment, serving onnx
Model serving infrastructure, TensorFlow Serving and ONNX Runtime being two widely used concrete examples, provides the actual production runtime environment that loads a trained…
model serving framework selection, model serving framework, serving framework selection, model serving, serving framework, framework selection
Model Serving Framework Selection Introduction & Motivation Model Serving Framework Selection addresses a central problem in ml-ops process control…
ml model deployment, model optimization serving, onnx runtime inference, triton inference server
ML Model Serving and Inference Optimization is the engineering discipline of deploying trained models into production systems that process real-time requests at scale — where…
tensorrt onnx runtime, deep learning deployment, inference acceleration, model optimization serving latency
Deep Learning Model Serving and Inference Optimization is the engineering discipline of deploying trained neural networks into production environments with minimal latency…
model serving inference optimization, model serving inference, serving inference optimization, model serving, serving inference, inference optimization
Model Serving Inference Optimization Introduction & Motivation Model Serving Inference Optimization addresses a central problem in systems process control…
model serving with memory contention and shared l3 cache, model serving memory, serving memory contention, memory contention shared, contention shared l3, shared l3 cache, shared l3
Model Serving with Memory Contention and Shared L3 Cache Introduction & Motivation Model Serving with Memory Contention and Shared L3 Cache addresses a central problem…
model serving and inference deployment, model serving inference, serving inference deployment, model serving, serving inference, inference deployment
Model Serving and Inference Deployment Introduction & Motivation Model Serving and Inference Deployment addresses a central problem in ml-inference process control…
infrastructure
Model Serving Platform is the infrastructure layer that deploys trained machine learning models as scalable, production-ready prediction services — abstracting away the complexity…
inference serving architecture, production model deployment, serving infrastructure, model serving frameworks
Model Serving Systems are the production infrastructure for deploying trained neural networks as scalable, reliable services — providing request handling, batching, load…
model training
Model size refers to the amount of storage space required to store a neural network's weights and associated metadata, determining the hardware requirements for loading, serving…
model merging
Model Soup is a model merging technique that averages the weights of multiple fine-tuned models — taking several models fine-tuned with different hyperparameters from the same…
privacy
Model stealing (model extraction) is an adversarial attack that reconstructs a functional replica of a proprietary machine learning model by systematically querying its prediction…
model merging
Model Stitching is a technique that combines layers from different pre-trained models into a single network — inserting a small "stitching layer" (typically a 1×1 convolution…
explainable ai
Model stitching for understanding is the technique that connects layers from different models with learned adapters to test representational compatibility - it probes whether…
extraction, protect
Model Extraction and Protection What is Model Extraction? Attacks that steal ML models by querying them and training a copy, enabling intellectual property theft and attack…
training, pre-training, fine-tuning, rlhf, tokenization, scaling laws, distributed training
Large language model training is the industrial-scale numerical optimization of hundreds of billions of transformer weights across distributed accelerator clusters, converting raw…
training steps, training duration
An epoch is one complete pass through the entire training dataset, a fundamental unit of training progress. Definition: Every example seen exactly once = one epoch. Multiple…
how are llms trained, how neural networks are trained, model training loop, how ai models are trained, gradient descent training, deep learning training
Training is the process of teaching a machine-learning model by repeatedly showing it data and adjusting its internal parameters — its weights — until its predictions match…
training monitoring
Early stopping halts training when validation performance stops improving, preventing overfitting. Mechanism: Monitor validation metric each epoch/N steps. If no improvement…
model uncertainty quantification, model uncertainty, uncertainty quantification
Model Uncertainty Quantification Introduction & Motivation Model Uncertainty Quantification addresses a central problem in ml-analysis process control…