diff --git a/common/sampling.h b/common/sampling.h
index 7804b4ffaf469..9bcc709b6fd05 100644
--- a/common/sampling.h
+++ b/common/sampling.h
@@ -4,7 +4,6 @@
 
 #include <string>
 #include <vector>
-#include <stdexcept>
 
 // sampler types
 enum class llama_sampler_type : char {
diff --git a/examples/speculative/speculative.cpp b/examples/speculative/speculative.cpp
index f9d38e5ec62a0..dc39974aa78f1 100644
--- a/examples/speculative/speculative.cpp
+++ b/examples/speculative/speculative.cpp
@@ -231,7 +231,7 @@ int main(int argc, char ** argv) {
                 if (params.sparams.temp > 0) {
                     // stochastic verification
 
-                    llama_token_data_array dist_tgt = llama_sampling_prepare(ctx_sampling, ctx_tgt, NULL, drafts[s_keep].i_batch_tgt[i_dft], true, NULL);
+                    llama_token_data_array dist_tgt = llama_sampling_prepare(ctx_sampling, ctx_tgt, NULL, drafts[s_keep].i_batch_tgt[i_dft]);
                     llama_sampling_softmax(ctx_sampling->smpl, &dist_tgt);
 
                     float p_tgt = 0.0f;
diff --git a/src/llama-impl.h b/src/llama-impl.h
index b435dfa548572..09b220a6cf6d7 100644
--- a/src/llama-impl.h
+++ b/src/llama-impl.h
@@ -4,6 +4,7 @@
 
 #include <string>
 #include <vector>
+#include <stdexcept>
 
 #ifdef __GNUC__
 #ifdef __MINGW32__