OpenAI Triton compiler fork for IBM POWER9/POWER10 (ppc64le) with CUDA 12.4. Tesla V100 sm70 GPU kernels for PyTorch and SGLang.
python machine-learning deep-learning compiler gpu cuda pytorch nvidia openai triton ppc64le volta power9 ibm-power triton-lang tesla-v100 cuda-12 sm70 gpu-compiler power10
-
Updated
Apr 16, 2026 - MLIR