Skip to main content Link Search Menu Expand Document (external link)
Last updated: | Permalink

Course Schedule

Being less concrete further out, the course scheduling is tentative and subject to changes.

Introduction, AI systems foundation

AI infrastructure

Week 4

09/14
Lec5-1: Hardware acceleration
Video

Reading: mlsysbook: Hardware Acceleration (required); Memory wall UVA tech report (optional); Roofline model UC Berkeley tech report (optional); OpenAI Jalapeño first results (optional)

09/16
Lec5-2: Hardware acceleration
Video

Reading see 09/14

Systolic array: Demo

Inference Speedrun artifact due (09/16)

09/17

Project team signup due (09/17)

Week 5

09/21

Lec6: AI compute communication

09/23

Lec7: AI network infrastructure

Model training paradigm and performance engineering

Week 6

09/28

Lec8: AI storage infrastructure

09/30

Lec9: FlashAttention

Project proposal due (09/30)

LLM inference

Week 7

10/05

Reading day (no class)

10/07

Lec10: Distributed training

Paper presentation signup due (10/07)

Week 8

10/12

Lec11: LLM inference II (vLLM, KVC, speculative decoding)

10/14

Lec12: AI agents

Student paper presentations, guest lectures

Week 9

10/19

TBD

10/21

TBD

Week 10

10/26

TBD

10/28

Project checkpoint presentation

Week 11

11/02

TBD

11/04

TBD

Week 12

11/09

TBD

11/11

TBD

Week 13

11/16

TBD

11/18

TBD

Inference Speedrun report due

Week 14

11/23

TBD

11/25

Thanksgiving recess (no class)

Week 15

11/30

Project presentation I

12/02

Project presentation II

Week 16

12/07

Project presentation III

12/09

Project everything due


© 2026 Yue Cheng. Released under the CC BY-SA license