happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Support -ctk f32

This commit is contained in:
Yu, Zijun 2026-01-07 16:56:30 +08:00 committed by Mustafa Cavus
parent f5c71e3cf4
commit 0d6f253e48
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-openvino/ggml-decoder.cpp
View File

@ -296,6 +296,9 @@ std::pair<ModelParams, ComputeParams> GgmlOvDecoder::compute_llm_params(ggml_cgr
std::string name = std::string(node->name);
if (node->op == GGML_OP_FLASH_ATTN_EXT) {
auto * cache_k_perm = node->src[1];
if (cache_k_perm->op == GGML_OP_CPY) {
cache_k_perm = cache_k_perm->src[0];
}
assert(cache_k_perm->op == GGML_OP_PERMUTE);
auto * cache_k_view = cache_k_perm->src[0];
assert(cache_k_view->op == GGML_OP_VIEW);