-
Retrieval-Augmented Generation (RAG)
RAG grounds LLM outputs in retrieved documents via sparse, dense, or hybrid search, improving factuality, citations, and freshness…
-
Grouped-Query Attention (GQA)
Grouped-Query Attention shares keys/values across groups of query heads, shrinking KV caches and bandwidth to speed LLM inference…
-
ReAct Prompting
ReAct prompting interleaves reasoning with tool actions and observations (Thought → Action → Observation), letting LLM agents plan,…
-
Toolformer
Toolformer teaches LMs to autonomously invoke external tools during generation by training on interleaved tool-call traces, boosting factuality…
-
Low-Rank Adaptation (LoRA)
LoRA fine-tunes LLMs by training small low-rank adapters on top of frozen weights, slashing memory and compute while…
-
FlashAttention
FlashAttention is an IO‑aware, exact attention algorithm that tiles work into GPU SRAM and fuses kernels to cut…
-
Paged Attention
Paged Attention organizes LLM KV caches into fixed-size pages to reduce fragmentation, enable continuous batching, and support long…
-
Vision-Language Model (VLM)
A Vision-Language Model (VLM) jointly learns from images and text to understand and generate multimodal content, enabling captioning,…
-
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…
-
Mixture of Experts (MoE)
Mixture of Experts (MoE) scales model capacity by routing each token to a small subset of expert networks,…
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.
-
Retrieval-Augmented Generation (RAG)
RAG grounds LLM outputs in retrieved documents via sparse, dense, or hybrid search, improving factuality, citations, and freshness…
-
Grouped-Query Attention (GQA)
Grouped-Query Attention shares keys/values across groups of query heads, shrinking KV caches and bandwidth to speed LLM inference…
-
ReAct Prompting
ReAct prompting interleaves reasoning with tool actions and observations (Thought → Action → Observation), letting LLM agents plan,…
-
Toolformer
Toolformer teaches LMs to autonomously invoke external tools during generation by training on interleaved tool-call traces, boosting factuality…
-
Low-Rank Adaptation (LoRA)
LoRA fine-tunes LLMs by training small low-rank adapters on top of frozen weights, slashing memory and compute while…
-
FlashAttention
FlashAttention is an IO‑aware, exact attention algorithm that tiles work into GPU SRAM and fuses kernels to cut…
-
Paged Attention
Paged Attention organizes LLM KV caches into fixed-size pages to reduce fragmentation, enable continuous batching, and support long…
-
Vision-Language Model (VLM)
A Vision-Language Model (VLM) jointly learns from images and text to understand and generate multimodal content, enabling captioning,…
-
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…
-
Mixture of Experts (MoE)
Mixture of Experts (MoE) scales model capacity by routing each token to a small subset of expert networks,…