KubeCon NA 2026
Alexa Griffith
●
Red Hat AI
Salt Lake City · slides, repos and everything from my talks
My talks
⚡
Cache Me If You Can: LLM Inference with llm-d
Wed Nov 11 · 11:00 · Hyatt Regency, Ballroom C
view slides
☁
Cloud Native With a Chance of Tokens
Tip Talk · Tue Nov 10 · 11:00
view slides
Try it yourself
▦
Flow control benchmarks
llm-d flow control experiments and results
→
⌥
Benchmark repo
configs, data and how to reproduce
→
▶
Flow Control Flight Recorder
inspect traffic, queues and engine activity over time
→
▶
Interactive flow control explainer
explore admission, queues and scheduling
→
✎
llm-d course
short animated lessons on llm-d
→
⚙
Shared inference learner
many teams, one GPU pool: how the pieces fit
→
Upstream projects
d
llm-d
Kubernetes-native distributed inference
→
⌥
llm-d router
the Endpoint Picker, flow control and scorers
→
v
vLLM
the model server under it all
→
Connect
in
LinkedIn
@alexa-griffith
→
⌥
GitHub
@alexagriffith
→
🎙
Alexa's Input (AI)
my podcast
→
✦
All my links
podcasts, writing, socials
→