Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

llm: patch to fix qwen 2 temporarily on nvidia (#4897)

Jeffrey Morgance0dc33cb809
diff --git a/llm/patches/06-qwen2.diff b/llm/patches/06-qwen2.diff
new file mode 100644
index 000000000..d7b0c1555
--- /dev/null
+++ b/llm/patches/06-qwen2.diff
@@ -0,0 +1,13 @@
+diff --git a/llama.cpp b/llama.cpp
+index 40d2ec2c..f34eb79a 100644
+--- a/llama.cpp
++++ b/llama.cpp
+@@ -6943,7 +6943,7 @@ static struct ggml_tensor * llm_build_kqv(
+ struct ggml_tensor * kq = ggml_mul_mat(ctx, k, q);
+ cb(kq, "kq", il);
+
+- if (model.arch == LLM_ARCH_PHI2 || model.arch == LLM_ARCH_PHI3 || model.arch == LLM_ARCH_GPTNEOX) {
++ if (model.arch == LLM_ARCH_PHI2 || model.arch == LLM_ARCH_PHI3 || model.arch == LLM_ARCH_GPTNEOX || model.arch == LLM_ARCH_QWEN2) {
+ // for this arch, we need to perform the KQ multiplication with F32 precision, otherwise we get NaNs
+ // ref: https://github.com/ggerganov/llama.cpp/pull/4490#issuecomment-1859055847
+ ggml_mul_mat_set_prec(kq, GGML_PREC_F32);