~/talk

ML inference acceleration on K8s using kata containers & AWS Firecracker

Talkat FOSDEM 2021 · on Sunday, 2021-02-07· at 17:00· D.containers· [kubernetes, machine-learning]

speaker

name:Orestis Lagkas Nikolos
links:none on file

resources

video:https://video.fosdem.org/2021/D.containers/containers_ml_kata.mp4
slides:https://fosdem.org/2021/schedule/event/containers_ml_kata/attachments/slides/4735/export/events/attachments/containers_ml_kata/slides/4735/Containers_NBFC_FOSDEM21.pdf

summary

Describes porting the vAccel framework for hardware acceleration to run inside AWS Firecracker microVMs managed as Kubernetes pods via Kata Containers. Covers the vAccel design and implementation, a kata-containers patch to support Firecracker v0.23.1, the Kubernetes integration steps to add vAccel, and a demo scaling GPU-backed image-classification microVMs across a K8s cluster.

AI-written summary · about

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.