Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

We introduce representative generative benchmarking—custom eval sets built from your own data that reflect real user queries. thank you @weights_biases for collaborating! link to report in replies https://t.co/IAo9eyjo1n

Chroma x.com

Performance. Benchmarked! w/ @oguzyagizkara for @ToDesktop https://t.co/nB33dKiX6z

Necati Koçlu x.com

(1/7) Do you want to test code generation models on the domains you care about? Struggling to find existing benchmarks that suit your needs? Our new work *CodeBenchGen* helps you build execution-based benchmarks based on your selected code fragments! (https://t.co/cWL6xXSkOg) https://t.co/B5l0O5qyd3

Yiqing Xie

x.com

quick Linux server benchmark with cpu, disk, and network tests https://t.co/iUb89pHqhy

Tom Dörr

x.com

Huge, if true! SWE-Bench is the most sophisticated software engineering benchmark: Claude 3 Opus purportedly scores 11.07% vs Devin's 13.86%

Deedy x.com

Dozens of teams have asked my advice on running LLMs. How fast is @deepseek_ai V3 with vLLM on 8 GPUs? What's the max throughput of @Alibaba_Qwen 2.5 Coder with SGLang on one H100? Running & sharing benchmarks ad hoc was too slow So we built a tiny app, the LLM Engine Advisor... See more

Charles 🎉 Frye x.com

You thought 68k was good, 90k is better 😏 Mac users, welcome to Mojo🔥! Download this Thursday at https://t.co/uUCIgici8E 🤘🏼💯 https://t.co/ku6VuNKT8n

Modular x.com

Pogocache : un cache Open Source écrit en C conçu pour offrir des temps de réponse rapides et une efficacité CPU élevée. Il peut être déployé comme serveur ou embarqué dans une application. 👉 Le projet : https://t.co/l32Y1x9xxf 👉 En savoir plus : https://t.co/MqXjrkmfXF... See more

bearstech

x.com

It even plots the data for you in the command line https://t.co/p80XUJlzgi

Tom Dörr

x.com