Schedule

  • This schedule is subject to change over the course of the semester.
  • Readings are to be completed before class.

Week 1

Tue
Basics Course Introduction
 
Friday
Basics Neural Networks and LLMs
 

Week 2

Tue
Basics Attention
 
Friday
Basics Training
 

Week 3

Tue
Basics Serving
 
Friday
Basics Fine-tuning
 

Week 4

Tue
Basics Optimization I
 
Friday
Basics Optimization II
 

Week 5

Tue
LLM Training State-of-the-art training
 
Friday
LLM Training Guest lecture or student speaker
 

Week 6

Tue
LLM Training Training parallelization
 
Friday
LLM Training Guest lecture or student speaker
 

Week 7

Tue
LLM Serving State-of-the-art serving
 
Friday
LLM Serving Guest lecture or student speaker
 

Week 8

Tue
LLM Serving KV cache
 
Friday
LLM Serving Guest lecture or student speaker
 

Week 9

Tue
LLM Serving Speculative decoding
 
Friday
LLM Serving Guest lecture or student speaker
 

Week 10

Tue
LLM Serving Prefill-decode separation
 
Friday
LLM Serving Guest lecture or student speaker
 

Week 11

Tue
LLM Optimization Compilation
 
Friday
LLM Optimization Guest lecture or student speaker
 

Week 12

Tue
LLM Optimization Quantization
 
Friday
LLM Optimization Guest lecture or student speaker
 

Week 13

Tue
LLM Optimization Sparsity
 
Friday
LLM Optimization Guest lecture or student speaker