ML model and tooling updates

One live stream of releases and blog posts from the ML frameworks and tooling your stack depends on.

Monitor Hugging Face, PyTorch, TensorFlow, LangChain, LlamaIndex, Ollama, vLLM, and Weights & Biases for new versions, breaking changes, and engineering posts. Release feeds are polled and deduplicated, and feed-less blogs are diffed on a schedule so you catch each real change once. Made for ML practitioners who need to know when a framework ships a new version or drops support for something you rely on. Each new release or post arrives as a single event you can wire into CI, chat, or a webhook.

• H
  Hugging Face blog https://huggingface.co/blog/feed.xml
  Feed every 1h
• G
  vLLM releases https://github.com/vllm-project/vllm/releases.atom
  Feed every 1h
• G
  Ollama releases https://github.com/ollama/ollama/releases.atom
  Feed every 1h
• G
  LlamaIndex releases https://github.com/run-llama/llama_index/releases.atom
  Feed every 1h
• G
  Weights & Biases releases https://github.com/wandb/wandb/releases.atom
  Feed every 1h
• B
  TensorFlow blog https://blog.tensorflow.org/feeds/posts/default
  Feed every 24h
• P
  PyTorch blog https://pytorch.org/blog/
  Web page every 6h
• W
  LangChain blog https://www.langchain.com/blog
  Web page every 6h

• New releases and versions release OR version OR changelog OR "now available" OR "v1" OR "v2"
• Breaking changes and deprecations "breaking change" OR deprecated OR deprecation OR migration OR removed OR "drops support"
• Inference and model support ("model support" OR quantization OR inference OR fine-tune OR fine-tuning) AND (new OR faster OR added)