Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/labeler.yml
#	.github/workflows/release.yml
#	examples/debug/debug.cpp
#	ggml/src/ggml-cuda/common.cuh
#	ggml/src/ggml-cuda/mmq.cuh
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/mtmd/CMakeLists.txt

src/llama-vocab.cpp

@@ -2797,8 +2797,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                     || t.first == "[EOS]" // Kimi-K2
                     || t.first == "<|end_of_text|>"
                     || t.first == "<end_of_utterance>" // smoldocling
-                    || t.first == "<eos>" // kcpp: added for gemma4
-                    || t.first == "<turn|>" // gemma4
+                    || t.first == "<eos>"            // gemma4
+                    || t.first == "<turn|>"          // gemma4
                     || t.first == "<|tool_response>" // gemma4
                     || t.first == "<｜end▁of▁sentence｜>" // deepseek-ocr
                ) {
@@ -2892,6 +2892,33 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                 LLAMA_LOG_WARN("%s: special_eog_ids contains both '<|return|>' and '<|call|>', or '<|calls|>' and '<|flush|>' tokens, removing '<|end|>' token from EOG list\n", __func__);
             }
         }
+
+        // workaround for gemma4 and paddleocr: do not include </s> as an eog token
+        {
+            bool has_tool_response = false;
+            bool has_s = false;
+
+            llama_token s_id = LLAMA_TOKEN_NULL;
+
+            for (auto tid : special_eog_ids) {
+                const auto & text = id_to_token[tid].text;
+                if (text == "<|tool_response>") {
+                    has_tool_response = true;
+                } else if (text == "</s>") {
+                    has_s = true;
+                    s_id = tid;
+                }
+            }
+
+            if (has_tool_response && has_s) {
+                special_eog_ids.erase(s_id);
+
+                auto & attr = id_to_token[s_id].attr;
+                attr = LLAMA_TOKEN_ATTR_NORMAL;
+
+                LLAMA_LOG_WARN("%s: special_eog_ids contains '<|tool_response>', removing '</s>' token from EOG list\n", __func__);
+            }
+        }
     }
 
     // build special tokens cache