LLM Inference Optimization & Serving Systems
LLM Inference Optimization & Serving Systems KV cache, Batching, Latency vs Throughput Introduction Large Language Models have become the foundation of modern…
Continue readingBILLION HOPES BLOG
AI KNOWLEDGE CENTRE
Deep knowledge insights on technical and academic aspects of AI and related topics
68 articles
Category: AI Knowledge Centre
Memory Mechanisms in LLMs
Memory Mechanisms in LLMs Context windows vs external memory, Retrieval vs compression Introduction Large Language Models are often described as intelligent systems…
Continue reading
Alignment Algorithms RLHF, DPO, and Beyond
Alignment Algorithms RLHF, DPO, and Beyond Reward models, Preference optimization Introduction As large language models (LLMs) scale in capability, the central challenge…
Continue reading
Decoding Strategies in Generative Models
Decoding Strategies in Generative Models Top-k, top-p, beam search; Temperature scaling Introduction Generative models, especially modern large language models, produce text one…
Continue reading
In-Context Learning & Emergent Behaviour
In-Context Learning & Emergent Behaviour Few-shot learning, Emergence vs memorization Introduction Modern AI systems – especially large language models (LLMs) – have…
Continue reading
Training Stability & Gradient Dynamics
Training Stability & Gradient Dynamics Gradient explosion/vanishing, Initialization, normalization Introduction Training deep neural networks is not just about choosing the right architecture…
Continue reading
Self-Supervised Learning Paradigms
Self-Supervised Learning Paradigms Contrastive learning, Masked modelling Introduction Self-Supervised Learning (SSL) has emerged as one of the most powerful paradigms in modern…
Continue reading
Bayesian Machine Learning & Probabilistic AI
Bayesian Machine Learning & Probabilistic AI Bayesian inference, Uncertainty estimation Introduction In the evolving landscape of artificial intelligence, one of the most…
Continue reading
Scaling Laws & Compute-Optimal Training
Scaling Laws & Compute-Optimal Training Chinchilla scaling; Data vs model trade-offs Introduction Over the past decade, the rapid advancement of artificial intelligence…
Continue reading