Files
whisper.cpp/ggml
Oliver SimonsandGeorgi Gerganov 808904277e CUDA: Fix non-contig rope (llama/19338)
* Rename variables + fix rope_neox

Seems memory layout is shared with Vulkan so we can port fix from
https://github.com/ggml-org/llama.cpp/pull/19299

* Fix rope_multi

* Fix rope_vision

* Fix rope_norm

* Rename ne* to ne0* for consistent variable naming

* cont : consistent stride names

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-02-15 21:44:37 +02:00
..