mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-11-11 14:22:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

CANN: Add MROPE and IMROPE support (#17401)

Browse Source 
* CANN: ROPE supports both MROPE and IMROPE.

1. Optimize the caching logic of rope_cache_init.
2. Add support for mRoPE and i-mRoPE.

Note that on Ascend 910B devices, it is necessary to disable FA
in CLIP and disable NZ-format conversion. These two issues are
still under investigation.

* Resolve review comments
This commit is contained in:
hipudding
2025-11-26 16:44:19 +08:00
committed by GitHub
parent f3a848a3b1
commit eeb5605de2
3 changed files with 404 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cann/ggml-cann.cpp
-7
View File
@@ -2480,13 +2480,6 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev, const ggml_ten
return false;
}
const int mode = ((const int32_t *) op->op_params)[2];
if (mode & GGML_ROPE_TYPE_MROPE) {
return false;
}
if (mode & GGML_ROPE_TYPE_VISION) {
return false;
}
if (op->src[0]->ne[0] > 896) {
return false;
}