mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-27 16:37:29 -05:00
* CUDA: fuse rms_norm + mul + rope (+ view + set_rows) * tests: add broadcast weight case to rms_norm_mul_rope * CUDA: check memory ranges before rms_norm rope fusion * CUDA: check memory ranges in rope set_rows fusion