diff --git a/examples/embd-input/embd-input-lib.cpp b/examples/embd-input/embd-input-lib.cpp
index 0480eee19..d5df68637 100644
--- a/examples/embd-input/embd-input-lib.cpp
+++ b/examples/embd-input/embd-input-lib.cpp
@@ -83,7 +83,7 @@ bool eval_float(void * model, float * input, int N){
         if (n_eval > n_batch) {
             n_eval = n_batch;
         }
-        if (llama_eval_embd(ctx, (input+i*n_emb), n_eval, n_past, params.n_threads, params.pp_threads)) {
+        if (llama_eval_embd(ctx, (input+i*n_emb), n_eval, n_past, params.n_threads, params.n_threads)) {
             fprintf(stderr, "%s : failed to eval\n", __func__);
             return false;
         }
@@ -104,7 +104,7 @@ bool eval_tokens(void * model, std::vector<llama_token> tokens) {
         if (n_eval > params.n_batch) {
             n_eval = params.n_batch;
         }
-        if (llama_eval(ctx, &tokens[i], n_eval, n_past, params.n_threads, params.pp_threads)) {
+        if (llama_eval(ctx, &tokens[i], n_eval, n_past, params.n_threads, params.n_threads)) {
             fprintf(stderr, "%s : failed to eval\n", __func__);
             return false;
         }
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp
index e931d7f39..6f732ce46 100644
--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@@ -74,7 +74,7 @@ int main(int argc, char ** argv) {
 
     if (params.embedding){
         if (embd_inp.size() > 0) {
-            if (llama_eval(ctx, embd_inp.data(), embd_inp.size(), n_past, params.n_threads, params.pp_threads)) {
+            if (llama_eval(ctx, embd_inp.data(), embd_inp.size(), n_past, params.n_threads, params.n_threads)) {
                 fprintf(stderr, "%s : failed to eval\n", __func__);
                 return 1;
             }
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp
index f75b1ec41..7ed661ec5 100644
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@@ -66,7 +66,7 @@ void perplexity(llama_context * ctx, const gpt_params & params) {
                 tokens[batch_start] = llama_token_bos();
             }
 
-            if (llama_eval(ctx, tokens.data() + batch_start, batch_size, j * n_batch, params.n_threads, params.pp_threads)) {
+            if (llama_eval(ctx, tokens.data() + batch_start, batch_size, j * n_batch, params.n_threads, params.n_threads)) {
                 fprintf(stderr, "%s : failed to eval\n", __func__);
                 return;
             }
@@ -233,7 +233,7 @@ void hellaswag_score(llama_context * ctx, const gpt_params & params) {
             }
 
             // Evaluate the query
-            if (llama_eval(ctx, query_embd.data(), query_embd.size(), 0, params.n_threads, params.pp_threads)) {
+            if (llama_eval(ctx, query_embd.data(), query_embd.size(), 0, params.n_threads, params.n_threads)) {
                 fprintf(stderr, "%s : failed to eval\n", __func__);
                 return;
             }
diff --git a/examples/save-load-state/save-load-state.cpp b/examples/save-load-state/save-load-state.cpp
index 4821fad5d..c8586718e 100644
--- a/examples/save-load-state/save-load-state.cpp
+++ b/examples/save-load-state/save-load-state.cpp
@@ -56,7 +56,7 @@ int main(int argc, char ** argv) {
     }
 
     // evaluate prompt
-    llama_eval(ctx, tokens.data(), n_prompt_tokens, n_past, params.n_threads, params.pp_threads);
+    llama_eval(ctx, tokens.data(), n_prompt_tokens, n_past, params.n_threads, params.n_threads);
 
     last_n_tokens_data.insert(last_n_tokens_data.end(), tokens.data(), tokens.data() + n_prompt_tokens);
     n_past += n_prompt_tokens;
@@ -93,7 +93,7 @@ int main(int argc, char ** argv) {
         last_n_tokens_data.push_back(next_token);
 
         printf("%s", next_token_str);
-        if (llama_eval(ctx, &next_token, 1, n_past, params.n_threads, params.pp_threads)) {
+        if (llama_eval(ctx, &next_token, 1, n_past, params.n_threads, params.n_threads)) {
             fprintf(stderr, "\n%s : failed to evaluate\n", __func__);
             llama_free(ctx);
             llama_free_model(model);
@@ -153,7 +153,7 @@ int main(int argc, char ** argv) {
         last_n_tokens_data.push_back(next_token);
 
         printf("%s", next_token_str);
-        if (llama_eval(ctx2, &next_token, 1, n_past, params.n_threads, params.pp_threads)) {
+        if (llama_eval(ctx2, &next_token, 1, n_past, params.n_threads, params.n_threads)) {
             fprintf(stderr, "\n%s : failed to evaluate\n", __func__);
             llama_free(ctx2);
             llama_free_model(model);
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 853cd74cd..10b666c1c 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -350,7 +350,7 @@ struct llama_server_context
             {
                 n_eval = params.n_batch;
             }
-            if (llama_eval(ctx, &embd[n_past], n_eval, n_past, params.n_threads, params.pp_threads))
+            if (llama_eval(ctx, &embd[n_past], n_eval, n_past, params.n_threads, params.n_threads))
             {
                 LOG_ERROR("failed to eval", {
                                                 {"n_eval", n_eval},
diff --git a/examples/simple/simple.cpp b/examples/simple/simple.cpp
index 5fc6074bc..f093da32a 100644
--- a/examples/simple/simple.cpp
+++ b/examples/simple/simple.cpp
@@ -123,7 +123,7 @@ int main(int argc, char ** argv)
         // Evaluate the tokens :
         //---------------------------------
 
-        if ( llama_eval( ctx , tokens_list.data() , int(tokens_list.size()) , llama_get_kv_cache_token_count( ctx ) , params.n_threads , params.pp_threads ) )
+        if ( llama_eval( ctx , tokens_list.data() , int(tokens_list.size()) , llama_get_kv_cache_token_count( ctx ) , params.n_threads , params.n_threads ) )
         {
             fprintf( stderr,  "%s : failed to eval\n" , __func__ );
             return 1;
diff --git a/llama.cpp b/llama.cpp
index 630a4357a..97c5e0cb0 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1782,7 +1782,7 @@ static bool llama_eval_internal(
                    int   n_tokens,
                    int   n_past,
                    int   n_threads,
-   		           int   pp_threads,
+                   int   pp_threads,
             const char * cgraph_fname) {
 
     LLAMA_ASSERT((!tokens && embd) || (tokens && !embd));