Last updated: | Permalink

Course Schedule

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

Introduction, AI systems foundation

Week 1

08/24

08/26

Lec1: Course introduction: Video

Reading: The Bitter Lesson (required); Hidden Technical Debt in Machine Learning Systems (optional); Software 2.0 (optional)

08/28

Inference Speedrun out

Week 2

08/31

Lec2: Numeric data types: Video 1; Video 2

Reading: Floating Point and IEEE 754 (optional); Using FP8 and FP4 with Transformer Engine (optional); Defeating Nondeterminism in LLM Inference (optional)

09/02

Lec3-1: Model quantization: Video

Reading: mlsysbook: Quantization and Precision (required); Building a quantization paradigm from first principles (optional)

Week 3

09/07

Lec3-2: Model compression: Video

Reading: ZipLLM [NSDI’26] (optional); TensorDex [SOSP’26] (optional)

Pickle safety: Demo

09/09

Lec4: Project introduction: Video

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

Lec6-1: AI computing infra, scaling laws: Video

Reading: mlsysbook: Compute Infrastructure (required); Hoffman et al. Scaling Laws (DeepMind) (required); Kaplan et al. Scaling Laws (OpenAI) (optional)

09/23

Lec6-2: AI computing infra, scaling laws: Video

Reading see 09/21

Reliability

Week 6

09/28

Lec7-1: AI storage infra, reliability: Video

Reading: mlsysbook: Storage Infrastructure (required); Marin Hero Pretraining Run (optional); Xiaomi MiMo RL Run (optional)

09/30

Lec7-2: AI storage infra, reliability: Video

Reading see 09/28

Project proposal due (09/30)

LLM inference and performance engineering

Week 7

10/05

Reading day (no class)

10/07

Lec8-1: Distributed training: Video

Reading: mlsysbook: Distributed Training (required); ZeRO paper (optional)

Week 8

10/12: Lec8-2: Distributed training; Paper presentation signup due (10/12)
10/14: Lec9: Speculative decoding

Student paper presentations

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