embed_pooled -> embd_pooled

llama.cpp

@@ -12619,14 +12619,14 @@ static int llama_decode_internal(
     std::vector<std::vector<llama_seq_id>> seq_id;
 
     // this indicates we are doing pooled embedding, so we ignore batch.logits and output all tokens
-    bool embed_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE;
+    const bool embd_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE;
 
     // count outputs
-    if (batch_all.logits && !embed_pooled) {
+    if (batch_all.logits && !embd_pooled) {
         for (uint32_t i = 0; i < n_tokens_all; ++i) {
             n_outputs += batch_all.logits[i] != 0;
         }
-    } else if (lctx.logits_all || embed_pooled) {
+    } else if (lctx.logits_all || embd_pooled) {
         n_outputs = n_tokens_all;
     } else {
         // keep last output only
@@ -12672,7 +12672,7 @@ static int llama_decode_internal(
         {
             int32_t n_outputs_new = 0;
 
-            if (u_batch.logits && !embed_pooled) {
+            if (u_batch.logits && !embd_pooled) {
                 for (uint32_t i = 0; i < n_tokens; i++) {
                     n_outputs_new += u_batch.logits[i] != 0;
                 }