CS349E: Efficient ML Infrastructure at Scale

Home Course Info

Basic Logistics

Instructors: Zain Asgar, Mark Horowitz, Fred Kjolstad, Priyanka Raina

CA: Usman Tariq

Quarter: Autumn 2026

Lecture Times: Tue, Thu 10:30 AM - 11:50 AM

Lecture Location: Lathrop 299

Office Hours

Fred: Tuesdays 1-2pm, CoDa E456 (Fred's office)

Mark: MWF 4:30-5:30pm, Packard 175 (Mark's office)

Priyanka: Wednesdays 4-5pm, Allen 114 (Priyanka's office)

Usman: Mondays 12:30-2:30pm, Zoom; Thursdays 1-3pm, Zoom

Grading

Assignments

All assignments are due at 11:59 PM on their due date.

Assignment 1: LLM Inference

Released Sep 24 (Thu), due Oct 1 (Thu).

Assignment 2: Disaggregated Inference

Released Oct 5 (Mon), due Oct 12 (Mon).

Assignment 3: Tensor Parallelism

Released Oct 12 (Mon), due Oct 19 (Mon).

Assignment 4: Kernel Writing

Released Oct 19 (Mon), due Oct 26 (Mon).

Students with Documented Disabilities

Students who may need an academic accommodation based on the impact of a disability must initiate the request with the Office of Accessible Education (OAE). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty. Unless the student has a temporary disability, Accommodation letters are issued for the entire academic year. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations. The OAE is located at 563 Salvatierra Walk (phone: 723-1066, URL: https://oae.stanford.edu/.)