Red Hat ran its own engineering org on open weights as customer zero. What the EnMaaS pilot (Praxis gateway + llm-d + vLLM) showed:
-> Scale: more than 1 trillion tokens processed in a single 30-day window.
-> Adoption: give developers frictionless access and they take it. Usage started 70/30 in favor of commercial frontier APIs and flipped to 30/70 toward internally hosted open weight models, with open weights gaining share every day.
-> Workload: Praxis intelligently routed the majority of routine coding and evaluation traffic away from external APIs to hosted open weight models.
-> Cost: shifting that traffic from frontier to self-hosted models on llm-d cut effective token spend 40 to 70% vs prior frontier pricing, depending on prompt caching and routing.
Here's how we did it:
https://t.co/58AyXbEg6t
Announcing the release of Swift 6! 🎉🎉🎉
🦺Extended memory safety protections
🪟Embedded and cross-platform support
🧪Swift Testing: parameterized, macro-based testing
Read more: https://t.co/DQihPkMDLj
@adzan_ Kena stereotype doi. Gw aja masih disangka nonis pas solat jumat di mesjid kompleks rumah bokap. Padahal gw solat di situ sedari mesjidnya baru dibuka wakaka.
Podman Desktop 1.12 is now available!
https://t.co/HkkORkt6vy
🦭Podman remote
🦭 macOS GPU support
🦭 Windows GPU support
🦭 Podman 5.2.0
🦭 Light mode out of experimental
🦭ConfigMaps, Secrets and multi-file Kubernetes YAML
🦭 plus more!
Download or update!
#containers#podman
I read @migueldeicaza tweet (https://t.co/CaymrR82XP), and I wonder how Java performs.
I use Quarkus 3.10.2 with OpenJDK 21 on Fedora 40 on Ryzen 9 5900X, 128GB. I run the app in JVM and Native mode.
JVM: 99992 Req/s
Native: 133342 Req/s
Native mode uses 100MB of memory.
I was wondering how Swift compared, on my Mac using Vapor in release mode and .NET 8 on Release Mode:
Swift 5.10: 64,728 req/sec
.NET 8: 61,461 req/sec
First time I do Swift on the server, so I have no idea what I am doing:
https://t.co/Fxqp00zeTP
Full package: https://t.co/J3AotzmRDh