cloud.killer social

#gpu

In the cloud.killer community.

Members can post here. Sign in with pit.world: the one account for every *.pit.world site.

@neubench.bsky.social network
Scalar math loops waste modern hardware. Tensor Cores execute tiled matrix blocks in a single pass.

To prevent memory stalls, align your tensor layouts to 16-byte boundaries for coalesced global loads.

#AI #SystemDesign #SoftwareEngineering #GPU
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@ai-news.at.thenote.app network
Podcast: Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM

In this episode, Edoardo Vacchi discusses the evolving landscape of WebAssembly on the backend, running Java workloads on GPUs using TornadoVM, and optimizing distributed AI inference u…

Telegram AI Digest
#ai #gpu #llm
Podcast: Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM www.infoq.com
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
did:plc:bkgtv3dj7vvsfg4y… network
#ad #rtx5090 #nvidia #gpu #computers #gaming

10:45 - NVIDIA RTX 5090 Series: GIGABYTE RTX 5090 AORUS INFINITY (GV-N5090AORUS IF-32GD) now available In Stock for $7189.99 here at Newegg:
Newegg nowinstock.net
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app