No matches.
↑↓ navigate↵ openesc close
We built Control Room, a central system to track model workloads across our research infrastructure and stop them quickly when safety or security concerns arise.
With AI models scaling fast, seamless orchestration is key.
New Anthropic research: progress on provable inference for large language models.
Great to see the open source community pushing inference performance forward on PyTorch: A megakernel for Muse Spark Open on TPU v7 got 433 tok/s per user and up to 25.9K tok/s per chip on AgentX (1M context).
At AIatAMD AMD AI DevDay in Austin sparkycollier spoke to a room full of developers on how the PyTorch Foundation is powering training, inference, and agents as the open source center of gravity.
vLLM relies heavily on PyTorch, with frequent calls to LibTorch in its C++ backend.
Join me and 2000 other AI engineers and builders at AI Dev in New York City, Nov 30-Dec 1!
What can you test on one GPU before a big PyTorch training run?
Muse Spark Open: 517 → 1,109 tokens/s on 8× GB300 with SGLang megakernels.
The OpenAI-Hugging Face hack was enabled by weak sandboxing.