diff --git a/examples/infill/infill.cpp b/examples/infill/infill.cpp
index 9542d7b6c..81e037265 100644
--- a/examples/infill/infill.cpp
+++ b/examples/infill/infill.cpp
@@ -235,7 +235,12 @@ int main(int argc, char ** argv) {
 
     std::vector<llama_token> embd_inp;
     std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
+    params.input_suffix.erase(0, params.input_suffix.find_first_not_of(" "));
     std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);
+    const int space_token = 29871;
+    if (params.escape && inp_sfx.size() > 1 && inp_sfx[0] == space_token) {
+        inp_sfx.erase(inp_sfx.begin());
+    }
     inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(ctx));
     if (add_bos) {
         inp_pfx.insert(inp_pfx.begin(), llama_token_bos(ctx));
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index fa5e52e82..53c0fb800 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -344,8 +344,13 @@ struct llama_server_context
 
     void loadInfill()
     {
+        params.input_suffix.erase(0, params.input_suffix.find_first_not_of(" "));
         auto prefix_tokens = tokenize(params.input_prefix, false);
         auto suffix_tokens = tokenize(params.input_suffix, false);
+        const int space_token = 29871;
+        if (params.escape && suffix_tokens.size() > 1 && suffix_tokens[0] == space_token) {
+            suffix_tokens.erase(suffix_tokens.begin());
+        }
         prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(ctx));
         prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(ctx)); // always add BOS
         prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(ctx));