Files
ik_llama.cpp/ggml-cuda.cu
Jiahao Li b0cd5d83b3 2x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)
* 2x faster (rms) norm cuda kernels

* Fix code style
2023-09-04 08:53:30 +02:00

251 KiB