[None][feat] reuse triton slicing kernel for GDN prefill transpose#12737

nv-guomingz merged 1 commit intoNVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom

nv-guomingz:user/guomingz/qwen3.5-fla-triton-slicenv-guomingz/TensorRT-LLM:user/guomingz/qwen3.5-fla-triton-sliceCopy head branch name to clipboard