Index
Symbols
4-bit NormalFloat (NF4) 215
32-bit floating point (fp32) 211, 212
A
acceptance tests 464
actions 437
Activate-aware Weight Quantization (AWQ) 313
advanced RAG
overview 117, 118
post-retrieval step 124-126
pre-retrieval steps 119-122
retrieval step 122-124
advanced RAG post-retrieval optimization
reranking 334-338
advanced RAG pre-retrieval optimizations 324
query expansion 324-328
self-querying 328-332
advanced RAG retrieval optimization
filtered vector search 332-334
advanced RAG techniques
exploring 321-324
post-retrieval optimization 334-338
pre-retrieval optimizations 324-332
retrieval optimization 332-334
alerting system 457, 458
alerts 473
AlpacaEval 264
Amazon Resource Name (ARN) 375
Application Auto Scaling 396, 397
Application Load Balancer (ALB) 395
asynchronous inference 361, 362
autoscaling 393, 399
scalable policy, creating 397
...