Running Open Models on Commodity GPUs

Proposed by Kwame Boateng · Anansi Systems

Draft

Decision

Currently draft. You can change your mind at any time.

Proposal

Draft: quantisation, paging and batching tricks for serving open-weight models on hardware you already own.

Infrastructure & ScaleWorkshopAdvanced

Open Source

Speaker

People attached to this proposal. Accepting copies them onto the session and assigns their onboarding tasks.

Kwame BoatengSpeakerPrimary contact

Staff Engineer, Anansi Systemskwame.boateng@example.com

Kwame works on inference runtimes and open-model deployment on hardware that was never meant for it.

Application answers

Everything the speaker filled in on the call-for-papers form.

Talk title: Running Open Models on Commodity GPUs
Abstract: Draft: quantisation, paging and batching tricks for serving open-weight models on hardware you already own.
Track(s): Infrastructure & Scale
Session format: Workshop (90 min)
Audience level: Advanced
Have you presented this talk before?: No
Do you need travel support to attend?: Yes
Speaker biography: Kwame works on inference runtimes and open-model deployment on hardware that was never meant for it.

Reviewers

Assign this proposal to a specific reviewer, on top of whoever already gets it through their tracks.

Reviews

0 reviews from the programme committee.

No reviews yet

Once reviewers score this proposal their comments show up here. You can still make a decision without them.

Details

FormatWorkshop

Audience levelAdvanced

SubmittedNot submitted yet

Decision recorded—

FormDevFlow Conf 2027 — Call for Speakers