CUDA
vLLM adopts LibTorch Stable ABI to ease PyTorch upgrades
vLLM has migrated its CUDA build to PyTorch’s LibTorch Stable ABI, allowing its v0.33.0 LibTorch ABI Stable CUDA wheels to work across compatible PyTorch releases…
NVIDIA CUDA 13.5 Brings Vera Rubin to General Availability
NVIDIA has released CUDA 13.5, which moves support for the Vera Rubin architecture from early developer access to general availability, according to the company. The…
For developersPyTorch's FBTriton Kernels for Table Batched Embeddings Beat Legacy CUDA
PyTorch has published a technical walkthrough of FBTriton, a Triton-based implementation of the Table Batched Embedding (TBE) forward and backward kernels used in…