thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)

Browse source 
* ggml-zennn: add ZenDNN backend support

* ggml-zendnn : address ZenDNN backend review fixes and suggestions

* docs : apply blockquote syntax to ZenDNN docs

---------

Co-authored-by: Manoj Kumar <mkumar@zettabolt.com>
This commit is contained in:
Vishal Singh 2025-12-06 21:43:33 +05:30 • committed by GitHub
parent c42712b056
commit 017761daf5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 19740 additions and 109 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tools/llama-bench/llama-bench.cpp
View file

@ -1737,7 +1737,8 @@ struct markdown_printer : public printer {
fields.emplace_back("params");
fields.emplace_back("backend");
bool is_cpu_backend = test::get_backend().find("CPU") != std::string::npos ||
test::get_backend().find("BLAS") != std::string::npos;
test::get_backend().find("BLAS") != std::string::npos ||
test::get_backend().find("ZenDNN") != std::string::npos;
if (!is_cpu_backend) {
fields.emplace_back("n_gpu_layers");
}