Skip to content

LLM inference in C/C++

C++ ggml

tests: re-enable MiniMax M3 in `test-llama-archs` (#26633)

Niklas Wenzel360e1349f000
diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp
index 1654f122a7..eb90798b62 100644
--- a/tests/test-llama-archs.cpp
+++ b/tests/test-llama-archs.cpp
@@ -432,7 +432,7 @@ 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 || arch == LLM_ARCH_MINIMAX_M3) {
+ if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA) {
return false;
}
#endif // GGML_USE_WEBGPU