tokenizers
fast, rust
Hugging Face Tokenizers is a high-performance text tokenization library written in Rust with Python bindings that converts raw text into the token sequences that language models…
1,520 technical terms and definitions
fast, rust
Hugging Face Tokenizers is a high-performance text tokenization library written in Rust with Python bindings that converts raw text into the token sequences that language models…
optimization
Tokens per second is the throughput metric for language-model workloads representing text units processed or generated per second - it is the standard speed measure for both LLM…
spc
Tolerance in semiconductor manufacturing is the allowable range of variation for a measured parameter — defined as the difference between the upper and lower specification limits…
quality & reliability
Tolerance Design is the economic allocation of tighter specifications to critical factors after robust parameter settings are chosen - It is a core method in modern semiconductor…
quality
Tombstoning is the reflow defect where one end of a small chip component lifts from the PCB and stands upright due to unbalanced wetting forces - it is a common challenge…
Tomek Links Detection for Boundary Cleaning Introduction & Motivation Tomek Links Detection for Boundary Cleaning addresses a central problem in {subject} assurance and {target}…
ai agent
Tool-Augmented LLMs are language models enhanced with the ability to invoke external tools, APIs, and services during generation — transforming LLMs from pure text generators into…
equipment availability, tool uptime availability
Tool availability measures the fraction of calendar time a semiconductor fabrication tool remains in a usable, productive state versus downtime. In fabs where cycle times span…
tool availability loss prediction, tool availability loss, availability loss prediction, tool availability, availability loss, loss prediction
Tool Availability Loss Prediction with Machine Learning Introduction & Motivation Tool Availability Loss Prediction with Machine Learning addresses a central problem…
ai agents
Tool use is the mechanism by which a language model, which can only ever generate text, reaches outside itself to search a database, run code, or call an API — by emitting…
ai agent
Tool calling with validation is the practice of verifying that an AI agent's generated function calls, API requests, or tool invocations have correct and safe arguments before…
production
Tool capacity planning is the process of determining required equipment count and utilization targets to meet forecast wafer demand with reliability headroom - it aligns…
process tool defect, defect signature, wafer defect, particle defect, tool-induced defect
Tool contamination is the equipment-originated transfer of particles, metals, residual films, ions, or organics to wafers. Its signature may be radial, backside, edge-localized…
ai agents
Tool Discovery is the capability-learning process by which agents identify available tools and usage constraints at runtime - It is a core method in modern semiconductor AI-agent…
ai agents
Tool Documentation is the structured description of tool purpose, inputs, outputs, and constraints for reliable agent usage - It is a core method in modern semiconductor AI-agent…
environmental & sustainability
Tool Idle Management is operational control that reduces utility consumption when manufacturing tools are not actively processing - It captures energy savings without major…
manufacturing
Tool-induced variation is the portion of process output variability caused by inherent differences or dynamic behavior within a specific tool - it reflects hardware, control…
tool use, function calling, tool calling, Model Context Protocol, MCP, Toolformer, sandboxing tools
Tool integration is the engineering of connecting a language model to external functions and services, such as search, a database, a calculator, a code interpreter or a company…
chamber matching, equipment qualification
Tool Matching Maintenance is a fab production strategy ensuring process tools of the same type produce equivalent results, minimizing chamber-to-chamber variation. What Is Tool…
tool matching qualification drift prediction, tool matching qualification, matching qualification drift, qualification drift prediction, tool matching, matching qualification
Tool Matching Qualification Drift Prediction with Machine Learning Introduction & Motivation Tool Matching Qualification Drift Prediction with Machine Learning addresses a central…
tool part remaining useful life supply alignment prediction, tool part remaining, part remaining useful, remaining useful life, useful life supply
Tool Part Remaining Useful Life Supply Alignment Prediction with Machine Learning Introduction & Motivation Tool Part Remaining Useful Life Supply Alignment Prediction…
production
Tool performance specifications is the subset of equipment requirements that defines expected operational output, reliability, and quality performance under normal use conditions…
tool pm kit consumable life prediction machine learning, tool pm, kit consumable life, pm, tool pm kit consumable life prediction, tool pm kit, pm kit consumable, pm kit
Tool PM Kit Consumable Life Prediction with Machine Learning Introduction & Motivation Tool PM Kit Consumable Life Prediction with Machine Learning addresses a central problem…
production
Tool qualification is the formal process of demonstrating that equipment installation, operation, and process performance meet defined requirements before production release - it…
qualification after pm, pm qualification, post-maintenance qualification
Tool qualification after preventive maintenance is the risk-scaled demonstration that the serviced semiconductor equipment is correctly assembled, safe, stable…
tool qualification engineer review cycle time prediction, tool qualification engineer, qualification engineer review, engineer review cycle, review cycle time
Tool Qualification Engineer Review Cycle Time Prediction with Machine Learning Introduction & Motivation Tool Qualification Engineer Review Cycle Time Prediction with Machine…
tool qualification sampling plan optimization prediction, tool qualification sampling, qualification sampling plan, sampling plan optimization, sampling plan
Tool Qualification Sampling Plan Optimization Prediction with Machine Learning Introduction & Motivation Tool Qualification Sampling Plan Optimization Prediction with Machine…
tool qualification wafer test prediction machine learning, tool qualification, wafer test prediction, tool qualification wafer test prediction, tool qualification wafer
Tool Qualification Wafer Test Prediction with Machine Learning Introduction & Motivation Tool Qualification Wafer Test Prediction with Machine Learning addresses a central problem…
ai agents
Tool Result Parsing is the extraction and normalization of raw tool outputs into compact machine-usable context - It is a core method in modern semiconductor AI-agent coordination…
tool use
Tool selection is the decision process that chooses the most appropriate tool for a given request - Selection policies map task intent context and constraints to available tools…
ai agents
Tool Selection is the process of choosing the most relevant tool from a larger capability set for a specific subtask - It is a core method in modern semiconductor AI-agent…
tool use
Tool sequencing is the ordered orchestration of multiple tool calls needed to complete multi-step tasks - Planning modules determine call order dependencies and stopping criteria…
production
A tool suite (or tool group) is the collection of identical or functionally equivalent equipment that performs the same process step in a semiconductor fab. Managing tool suites…
tool swap process drift risk prediction, tool swap process, swap process drift, process drift risk, drift risk prediction, tool swap, swap process, process drift, drift risk
Tool Swap Process Drift Risk Prediction with Machine Learning Introduction & Motivation Tool Swap Process Drift Risk Prediction with Machine Learning addresses a central problem…
production
Tool-to-tool matching is the practice of ensuring that different process tools (chambers) produce identical or near-identical results when running the same recipe. In…
tool to tool matching and chamber fingerprinting, tool tool matching chamber fingerprinting, tool tool, matching chamber fingerprinting, tool-to-tool matching chamber, tool-to-tool matching
Tool-to-Tool Matching and Chamber Fingerprinting Introduction & Motivation Tool-to-Tool Matching and Chamber Fingerprinting addresses a central problem in equipment fleet…
tool tool matching qualification prediction, tool-to-tool matching, tool tool matching, tool-to-tool matching qualification, matching qualification prediction, matching qualification
Tool-to-Tool Matching Qualification Prediction with Machine Learning Introduction & Motivation Tool-to-Tool Matching Qualification Prediction with Machine Learning addresses…
tool-to-tool recipe portability prediction, tool-to-tool recipe portability, recipe portability prediction, tool-to-tool recipe, recipe portability, portability prediction
Tool-to-Tool Recipe Portability Prediction with Machine Learning Introduction & Motivation Tool-to-Tool Recipe Portability Prediction with Machine Learning addresses a central…
manufacturing operations
Tool-to-Tool Variation is the portion of process variability attributable to differences between tools running the same step - It is a core method in modern semiconductor…
prompting techniques
Tool use is the mechanism by which a language model, which can only ever generate text, reaches outside itself to search a database, run code, or call an API — by emitting…
evaluation
Tool use evaluation is measurement of how accurately safely and efficiently models invoke external tools - Evaluation tracks call validity argument correctness task completion…
ai agent
Tool use enables LLMs to invoke external APIs, functions, and systems to extend their capabilities. Capabilities extended: Real-time information (web search, APIs), computation…
fine-tuning
Tool use training is training models to decide when and how to call external tools during task execution - The model learns tool selection, argument construction, and result…
production
Tool utilization optimization is the improvement of productive processing share of total available tool time without harming quality or reliability - it focuses on converting…
tool utilization rate forecast prediction, tool utilization rate, utilization rate forecast, rate forecast prediction, tool utilization, utilization rate, rate forecast
Tool Utilization Rate Forecast Prediction with Machine Learning Introduction & Motivation Tool Utilization Rate Forecast Prediction with Machine Learning addresses a central…
production
Tool warm-up is the controlled startup procedure that brings equipment thermal, mechanical, and process conditions to stable operating state - it reduces startup variability…
tool wear prediction cutting tool prediction, tool wear prediction, wear prediction cutting, prediction cutting tool, cutting tool prediction, tool wear, wear prediction
Tool Wear Prediction Cutting Tool Prediction with Machine Learning Introduction & Motivation Tool Wear Prediction Cutting Tool Prediction with Machine Learning addresses a central…
evaluation
ToolBench is a benchmark framework for assessing large-language-model tool-use capabilities across diverse APIs - ToolBench datasets simulate realistic tool invocation tasks…
ai agents
ToolBench is a benchmark framework focused on selecting and invoking external APIs and tools correctly - It is a core method in modern semiconductor AI-agent engineering…
tool, meta
Toolformer is a seminal research paper by Meta AI that demonstrated language models can teach themselves to use external tools (calculators, search engines, calendars, translation…