NVIDIA details cuTile kernels for Mamba-2 forward pass

NVIDIA said it has used its cuTile Python DSL to implement and optimize the forward pass of Mamba-2, a sequence model used by Jane Street engineers in an early adoption effort. The Oct. 19, 2026 post describes three custom kernels and reports that the optimized cuTile version ran 1.14x to 1.82x faster than an open source Triton implementation in the benchmark setup NVIDIA disclosed. According to NVIDIA’s Oct. 19, 2026 developer blog, cuTile is a Python-based DSL and programming model for NVIDIA GPUs that abstracts thread- and warp-level scheduling behind tile-centric primitives.

Source: Blockchain.News