Slides: How fast are LLM inference engines anyway? — Charles Frye, Modal

Source Video

How fast are LLM inference engines anyway? — Charles Frye, Modal

Relationship To World's Fair 2026

These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

Related Scheduled Sessions

Extracted Slides

slide-001.jpg

OCR text:

aWS

ee)

@®Graphite W Windsurf 4 MoneobB

Mdaily £3augmentcode WorkOS

slide-002.jpg

OCR text:

Open weights models

and open source engines

are getting better very quickly.

It finally makes sense to self-host!

) ‘| f a Microsoft art?

slide-003.jpg

OCR text:

. Biides iAlNnnr

.

ge eS <2" 5 F :

peer “oe ,

DOM ose

ieee 40° -

cor 0" ee _ ae

bit. ly/ai-engineer-201-2023

| by Chares Frye

2

| ‘ , a Microsoft aur?

slide-004.jpg

OCR text:

J

If capabilities requirements

saturate, open models will

catch up, then dominate.

/ ‘ 7 a Microsoft ary?

slide-005.jpg

OCR text:

Check out specialized LLM inference libraries.

oa | ace mE an oerG le aero il Bat is Steen ee a aera

. A,

slide-006.jpg

OCR text:

Let'sexplorewiththeLLMEngineAdvisor!

Iwanto serveLam3I s8

with

Clients should receivethe first tokeIn under

anyengine

1second

128tokensin/1024tok

every benchmarked

AIE

Copy

OELCAO_PATH

I0RS+40ENGTES

isupe-(

sodsl.leage froe_egistry

s:s/

modal.com/1lm-almanac

aws

World's Fair

slide-007.jpg

OCR text:

eal a ee

os 5 ue ee :

soa vee 5 o * O

LLM Engine Advisor wat Tenvtertveg crane

Teeeto wis Lhe SS voowuh Clem waitin: the finiieken Ry wee

any cogine ¥ Peecomd YP ethene

laApAtonacoge Stokeesie 2d rokemow v Iwonttouy every benchmarked Yo eet eraticen

;

* Thonaghper tngacsts oper repiaal vece

_ e

e uw Microsoft § eoou°

Works Fine

slide-008.jpg

OCR text:

Al Engineer

World's Fair

Slide-Derived Subjects To Review

Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.