AI Systems · Comparisons and explanations
RAG versus fine-tuning
Compare runtime evidence retrieval with parameter training through update behavior, authorization, evaluation, and combined designs.
IntermediateSEARCH LAVACS
Search textbooks, study guides, six encyclopedias, experiments and comparisons.
16 results · page 1 of 1
AI Systems · Comparisons and explanations
Compare runtime evidence retrieval with parameter training through update behavior, authorization, evaluation, and combined designs.
IntermediateAI Systems · Experiments and implementations
Rank fixed small vectors against explicit relevance judgments and calculate per-query and aggregated recall independently of vector similarity.
IntermediateAI Systems · Experiments and implementations
Use a deterministic queueing model to compare batch setup savings with individual request latency, without claiming GPU benchmark results.
IntermediateAI Systems · Experiments and implementations
Calculate live KV payload, page-rounded allocation, and maximum-length reservation from explicit per-request lengths.
IntermediateAI Systems · Experiments and implementations
Measure reconstruction under a uniform integer grid and vary step size, outliers, and clipping as separate experimental factors.
IntermediateAI Systems · Experiments and implementations
Compare fixed windows, overlapping windows, and a complete semantic unit on a tiny rule-and-exception document with a top-one retrieval budget.
IntermediateAI Systems · Study guides
Estimate GPU work using both operations and bytes, and compare batch size, queueing delay and memory demand with explicit assumptions.
AdvancedAI Systems · Study guides
Evaluate answer quality, service latency and information exposure separately, then trace failures across retrieval, generation and tool execution.
AdvancedAI Systems · Study guides
Design a retrieval and generation pipeline by separating document boundaries, search coverage, access control and support for the final answer.
AdvancedAI Systems · Study guides
Calculate compute and traffic lower bounds with explicit units and distinguish reuse, batching, and measurement from peak hardware limits.
IntermediateAI Systems · Study guides
Separate prompt processing from sequential generation through attention work, KV reuse, and explicitly defined timing intervals.
IntermediateAI Systems · Study guides
Define user-facing objectives for first-token delay, generation cadence, completion time, and rejected requests without hiding queueing or failures.
IntermediateAI Systems · Study guides
Calculate cache capacity with KV heads and allocation policy, distinguishing used positions, reservations, and total model-serving memory.
IntermediateAI Systems · Study guides
Separate quantization scale, rounding, and clipping, then examine outliers, layer-specific sensitivity, and actual execution formats.
IntermediateAI Systems · Study guides
Fix relevance judgments and evaluation units, aggregate precision and recall, and diagnose retrieval separately from generation.
IntermediateAI Systems · Design patterns and optimization
Reason about amortized overhead, batch formation delay, size limits, deadlines, and failure boundaries.
Intermediate