-
Reinforcement Learning from Human Feedback (RLHF)
RLHF aligns language models by training a reward model on human preferences and optimizing the policy with RL…
-
Key-Value Cache (KV Cache)
A KV cache stores past attention keys/values so LLMs reuse them at each step, cutting latency, enabling continuous…
-
Model Quantization
Model quantization reduces precision (e.g., INT8/INT4) for weights and activations to shrink memory and speed inference, enabling cheaper,…
-
Vector Database
A vector database indexes high‑dimensional embeddings for fast similarity search with metadata filters and hybrid retrieval—foundational for RAG,…
-
In-Context Learning (ICL)
ICL lets LLMs infer tasks from prompt-only examples—no weight updates—enabling zero/few-shot classification, extraction, and reasoning with schema-following in…
-
Paged Attention
Paged Attention organizes LLM KV caches into fixed-size pages to reduce fragmentation, enable continuous batching, and support long…
-
FlashAttention
FlashAttention is an IO‑aware, exact attention algorithm that tiles work into GPU SRAM and fuses kernels to cut…
-
Low-Rank Adaptation (LoRA)
LoRA fine-tunes LLMs by training small low-rank adapters on top of frozen weights, slashing memory and compute while…
-
ReAct Prompting
ReAct prompting interleaves reasoning with tool actions and observations (Thought → Action → Observation), letting LLM agents plan,…
-
Retrieval-Augmented Generation (RAG)
RAG grounds LLM outputs in retrieved documents via sparse, dense, or hybrid search, improving factuality, citations, and freshness…
ai search
Ask me anything. I will answer your question based on my website database.
Stay Connected
Subscribe to our newsletters. We’ll keep you in the loop.
-
Reinforcement Learning from Human Feedback (RLHF)
RLHF aligns language models by training a reward model on human preferences and optimizing the policy with RL…
-
Key-Value Cache (KV Cache)
A KV cache stores past attention keys/values so LLMs reuse them at each step, cutting latency, enabling continuous…
-
Model Quantization
Model quantization reduces precision (e.g., INT8/INT4) for weights and activations to shrink memory and speed inference, enabling cheaper,…
-
Vector Database
A vector database indexes high‑dimensional embeddings for fast similarity search with metadata filters and hybrid retrieval—foundational for RAG,…
-
In-Context Learning (ICL)
ICL lets LLMs infer tasks from prompt-only examples—no weight updates—enabling zero/few-shot classification, extraction, and reasoning with schema-following in…
-
Paged Attention
Paged Attention organizes LLM KV caches into fixed-size pages to reduce fragmentation, enable continuous batching, and support long…
-
FlashAttention
FlashAttention is an IO‑aware, exact attention algorithm that tiles work into GPU SRAM and fuses kernels to cut…
-
Low-Rank Adaptation (LoRA)
LoRA fine-tunes LLMs by training small low-rank adapters on top of frozen weights, slashing memory and compute while…
-
ReAct Prompting
ReAct prompting interleaves reasoning with tool actions and observations (Thought → Action → Observation), letting LLM agents plan,…
-
Retrieval-Augmented Generation (RAG)
RAG grounds LLM outputs in retrieved documents via sparse, dense, or hybrid search, improving factuality, citations, and freshness…