Skip to content

LLM inference in C/C++

C++ ggml

tests : exclude HY_V4 from WebGPU test-llama-archs tests (#28855)

fairydreaming5f436dddb440
diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp
index 3496f72e49..018ff1f42c 100644
--- a/tests/test-llama-archs.cpp
+++ b/tests/test-llama-archs.cpp
@@ -563,7 +563,8 @@ 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 || arch == LLM_ARCH_DOTS3NOTE || arch == LLM_ARCH_QWEN4EXP) {
+ if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_DOTS3NOTE || arch == LLM_ARCH_QWEN4EXP ||
+ arch == LLM_ARCH_HY_V4) {
return false;
}
#endif // GGML_USE_WEBGPU