UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models
Paper • 2607.23373 • Published • 7
🏗️ Building on HF
Yasharth Panwar
Yashp2003
AI & ML interests
None yet
Recent Activity
reacted to TravisMuhlestein's post with ❤️ 5 days ago
One of the most underrated parts of AI-assisted engineering may have nothing to do with the model.
It's the infrastructure around the engineer.
Shriyash Balshetwar and Shubham Jangle, engineers at GoDaddy, were spending roughly 16 mechanical pull requests per week managing localization branches. None of the work was particularly difficult—it was repetitive, easy to forget, and occasionally capable of blocking releases.
They built a GitHub App to remove the entire workflow.
What I find interesting is what happened underneath the simple idea of "automate the PRs."
The production system needed idempotent webhook handling, installation-scoped authentication, retry logic around GitHub's asynchronous mergeability state, per-repository configuration, and safe pattern matching.
The app itself is under 900 lines of JavaScript.
The interesting lesson is that the hard part of automation isn't always the automation.
It's building the reliability around it.
As AI agents take on more software engineering tasks, I expect this distinction to become even more important. The systems surrounding an agent—events, permissions, state, retries, validation, and feedback—may matter as much as the model making the decision.
🔗 https://www.godaddy.com/resources/news/how-a-github-app-saved-us-hours-of-manual-effort
Curious what other engineering workflows people have found worth automating end-to-end. reacted to danielhanchen's post with 👀 7 days ago
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: https://huggingface.co/unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5 reacted to danielhanchen's post with 😎 7 days ago
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: https://huggingface.co/unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5Organizations
upvoted a paper 21 days ago
upvoted a collection about 1 month ago
upvoted a collection 2 months ago