Skip to content

LLM inference in C/C++

C++ ggml

tests : disable DOTS3NOTE arch test for WebGPU (#27654)

fairydreaming7584430716ee
diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp
index 83922c53bd..b8fd66ccae 100644
--- a/tests/test-llama-archs.cpp
+++ b/tests/test-llama-archs.cpp
@@ -507,7 +507,7 @@ static bool arch_supported(const llm_arch arch) {
}
// FIXME: these hit scheduler/view-backed-output issues with WebGPU on CI.
#ifdef GGML_USE_WEBGPU
- if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA) {
+ if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_DOTS3NOTE) {
return false;
}
#endif // GGML_USE_WEBGPU