Skip to content

LLM inference in C/C++

C++ ggml

model : re-enable -sm tensor for qwen4exp (#28569)

Kevin Hopper10f340d1a2b0
diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp
index f72164ddb7..7ed8f8c86e 100644
--- a/src/llama-arch.cpp
+++ b/src/llama-arch.cpp
@@ -1171,7 +1171,6 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
case LLM_ARCH_KIMI_K3:
case LLM_ARCH_GLM5_NEXT:
case LLM_ARCH_QWEN3TTS:
- case LLM_ARCH_QWEN4EXP: // TODO: fix test-llama-archs
return false;
default:
return true;
diff --git a/src/models/qwen4exp.cpp b/src/models/qwen4exp.cpp
index 13f3c19f3d..168bc52945 100644
--- a/src/models/qwen4exp.cpp
+++ b/src/models/qwen4exp.cpp
@@ -393,6 +393,8 @@ llama_model_qwen4exp::graph::graph(const llama_model & model, const llm_graph_pa
ggml_reshape_3d(ctx0, inpL, n_embd, 1, n_tokens),
n_embd, hc, n_tokens, 1);
cb(res_hc, "hc_init", -1);
+ // make sure hc_init is in the same graph split as the first layer (-sm tensor)
+ ggml_build_forward_expand(gf, res_hc);
for (int il = 0; il < n_layer; ++il) {
res->t_layer_inp[il] = res_hc;