So much inspiration from you and what you built for the open-source community. Legend!
CODE
-
Accelerate GPU Training in Colab with TPU Runtime and steps_per_execution
By
–
If you're using Colab and you feel like training your model on GPU is slow, switch to the TPU runtime and tune the "steps_per_execution" parameter in model.compile() (higher = more work being done on device before moving back to host RAM) Can often see a 4-5x speedup.
-
Best practices for testing your Gradio app
By
–
Best practices for testing your Gradio app 👇 https://t.co/b2odKWCVZf
— Hugging Face (@huggingface) 6 novembre 2025Best practices for testing your Gradio app
-
PyTorch Contributor Recognized for Framework Growth
By
–
I hope your skin keeps glowing because of PyTorch 😀
jk jk.
You did more to help PyTorch's growth, and then to help course-correct PyTorch several times than you realize. Thanks for your ongoing service. I hope you continue using it for the next like 30 years, even after we get -
Start Your Next Legendary Streak with PyTorch
By
–
maybe you gotta start your next legendary streak… on @PyTorch
-
Building a Typescript Deep Research Agent with DeepAgents
By
–
Building a Typescript deep research agent In this video, we will walk through how to easily build a Typescript deep research agent This builds upon our new DeepAgents library All it involves is some detailed prompting, some search tools, and some specialized sub agents
-
Soumith Chintala Leaves Meta and PyTorch Leadership
By
–
Leaving Meta and PyTorch https://
soumith.ch/blog/2025-11-0
6-leaving-meta-and-pytorch.md.html
… -
Comet Assistant Gets Major Performance Upgrades Multi-Tab Support
By
–
Today we're rolling out major upgrades that significantly improve the performance and overall outcomes of the Comet Assistant. Comet can now handle more complex, multi-site workflows while working across multiple tabs in parallel.
-
Building Streaming Agents in Next.js with LangChain
By
–
Excellent walkthrough of how to build a streaming agent in @nextjs using LangChain. Clear explanation of server-sent events, UI streaming, and memory via thread IDs. If you’re evaluating production agent architectures, this is a strong reference implementation. Watch the
-
MIT Study Charts Legible Path for LLM-Assisted Programming
By
–
While programming w/LLMs seems promising, code can be messy, opaque, & hard to change safely. An MIT case study charts a more legible, modular path forward for software, bringing together features that'd otherwise be scattered across multiple services: https://
bit.ly/4pg2sBJ