Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	ggml/src/CMakeLists.txt

common/arg.cpp

@@ -1958,6 +1958,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.n_ctx_checkpoints = value;
         }
     ).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
+    add_opt(common_arg(
+        {"--cache-ram", "-cram"}, "N",
+        string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)\n"
+            "[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)", params.cache_ram_mib),
+        [](common_params & params, int value) {
+            params.cache_ram_mib = value;
+        }
+    ).set_env("LLAMA_ARG_CACHE_RAM").set_examples({LLAMA_EXAMPLE_SERVER}));
     add_opt(common_arg(
         {"--kv-unified", "-kvu"},
         string_format("use single unified KV buffer for the KV cache of all sequences (default: %s)\n"

common/chat.h

@@ -33,8 +33,8 @@ struct common_chat_msg_content_part {
 struct common_chat_msg {
     std::string role;
     std::string content;
-    std::vector<common_chat_msg_content_part> content_parts = {};
-    std::vector<common_chat_tool_call> tool_calls = {};
+    std::vector<common_chat_msg_content_part> content_parts;
+    std::vector<common_chat_tool_call> tool_calls;
     std::string reasoning_content;
     std::string tool_name;
     std::string tool_call_id;
@@ -44,7 +44,7 @@ struct common_chat_msg {
     bool empty() const {
         return content.empty() && content_parts.empty() && tool_calls.empty() && reasoning_content.empty() && tool_name.empty() && tool_call_id.empty();
     }
-    void ensure_tool_call_ids_set(std::vector<std::string> & ids_cache, const std::function<std::string()> & gen_tool_call_id) {
+    void set_tool_call_ids(std::vector<std::string> & ids_cache, const std::function<std::string()> & gen_tool_call_id) {
         for (auto i = 0u; i < tool_calls.size(); i++) {
             if (ids_cache.size() <= i) {
                 auto id = tool_calls[i].id;

common/common.h

@@ -374,7 +374,7 @@ struct common_params {
     bool simple_io         = false; // improves compatibility with subprocesses and limited consoles
     bool cont_batching     = true;  // insert new sequences for decoding on-the-fly
     bool no_perf           = false; // disable performance metrics
-    bool ctx_shift         = false;  // context shift on infinite text generation
+    bool ctx_shift         = false; // context shift on infinite text generation
     bool swa_full          = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
     bool kv_unified        = false; // enable unified KV cache
 
@@ -421,7 +421,8 @@ struct common_params {
     int32_t timeout_write     = timeout_read; // http write timeout in seconds
     int32_t n_threads_http    = -1;           // number of threads to process HTTP requests (TODO: support threadpool)
     int32_t n_cache_reuse     = 0;            // min chunk size to reuse from the cache via KV shifting
-    int32_t n_ctx_checkpoints = 3;            // max number of context checkpoints per slot
+    int32_t n_ctx_checkpoints = 8;            // max number of context checkpoints per slot
+    int32_t cache_ram_mib     = 8192;         // 0 = no limit, 1 = 1 MiB, etc.
 
     std::string hostname      = "127.0.0.1";
     std::string public_path   = "";                                                                         // NOLINT

ggml/src/ggml-cpu/ops.cpp

@@ -3467,31 +3467,27 @@ static void ggml_compute_forward_norm_f32(
 
     GGML_ASSERT(eps >= 0.0f);
 
-    // TODO: optimize
     for (int64_t i03 = 0; i03 < ne03; i03++) {
         for (int64_t i02 = 0; i02 < ne02; i02++) {
             for (int64_t i01 = ith; i01 < ne01; i01 += nth) {
                 const float * x = (float *) ((char *) src0->data + i01*nb01 + i02*nb02 + i03*nb03);
 
-                ggml_float sum = 0.0;
-                for (int64_t i00 = 0; i00 < ne00; i00++) {
-                    sum += (ggml_float)x[i00];
-                }
-
+                float sum = 0.0;
+                ggml_vec_sum_f32(ne00, &sum, x);
                 float mean = sum/ne00;
 
                 float * y = (float *) ((char *) dst->data + i01*nb1 + i02*nb2 + i03*nb3);
+                float variance = 0;
 
-                ggml_float sum2 = 0.0;
-                for (int64_t i00 = 0; i00 < ne00; i00++) {
-                    float v = x[i00] - mean;
-                    y[i00] = v;
-                    sum2 += (ggml_float)(v*v);
-                }
+#ifdef GGML_USE_ACCELERATE
+                mean = -mean;
+                vDSP_vsadd(x, 1, &mean, y, 1, ne00);
+                vDSP_measqv(y, 1, &variance, ne00);
+#else
+                variance = ggml_vec_cvar_f32(ne00, y, x, mean);
+#endif //GGML_USE_ACCELERATE
 
-                float variance = sum2/ne00;
                 const float scale = 1.0f/sqrtf(variance + eps);
-
                 ggml_vec_scale_f32(ne00, y, scale);
             }
         }

ggml/src/ggml-cpu/vec.cpp

@@ -404,6 +404,72 @@ void ggml_vec_swiglu_f32(const int n, float * y, const float * x, const float *
     }
 }
 
+ggml_float ggml_vec_cvar_f32(const int n, float * y, const float * x, const float mean) {
+    int i = 0;
+    ggml_float sum = 0;
+// TODO: optimize to process the remaining elements in groups using the smaller vector sizes from AVX2 and SSE
+// ref: https://github.com/ggml-org/llama.cpp/pull/15953#pullrequestreview-3310928344
+#if defined(__AVX512F__) && defined(__AVX512DQ__)
+    for (; i + 15 < n; i += 16) {
+        __m512 val = _mm512_sub_ps(_mm512_loadu_ps(x + i),
+                                   _mm512_set1_ps(mean));
+        _mm512_storeu_ps(y + i, val);
+        sum += (ggml_float)_mm512_reduce_add_ps(_mm512_mul_ps(val, val));
+    }
+#elif defined(__AVX2__) && defined(__FMA__)
+    for (; i + 7 < n; i += 8) {
+        __m256 val = _mm256_sub_ps(_mm256_loadu_ps(x + i),
+                                   _mm256_set1_ps(mean));
+        _mm256_storeu_ps(y + i, val);
+        val = _mm256_mul_ps(val,val);
+        __m128 val2 = _mm_add_ps(_mm256_extractf128_ps(val, 1),
+                                 _mm256_castps256_ps128(val));
+        val2 = _mm_add_ps(val2, _mm_movehl_ps(val2, val2));
+        val2 = _mm_add_ss(val2, _mm_movehdup_ps(val2));
+        sum += (ggml_float)_mm_cvtss_f32(val2);
+    }
+#elif defined(__SSE2__)
+    for (; i + 3 < n; i += 4) {
+        __m128 val = _mm_sub_ps(_mm_loadu_ps(x + i),
+                                _mm_set1_ps(mean));
+        _mm_storeu_ps(y + i, val);
+        val = _mm_mul_ps(val, val);
+#if defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__)
+        val = _mm_add_ps(val, _mm_movehl_ps(val, val));
+        val = _mm_add_ss(val, _mm_movehdup_ps(val));
+#else
+        __m128 tmp = _mm_shuffle_ps(val, val, _MM_SHUFFLE(2, 3, 0, 1));
+        val = _mm_add_ps(val, tmp);
+        tmp = _mm_movehl_ps(tmp, val);
+        val = _mm_add_ss(val, tmp);
+#endif  // __AVX__ || __AVX2__ || __AVX512F__
+        sum += (ggml_float)_mm_cvtss_f32(val);
+    }
+#elif defined(__ARM_NEON) && defined(__aarch64__)
+    for (; i + 3 < n; i += 4) {
+        float32x4_t val = vsubq_f32(vld1q_f32(x + i),
+                                    vdupq_n_f32(mean));
+        vst1q_f32(y + i, val);
+        val = vmulq_f32(val, val);
+        sum += (ggml_float)vaddvq_f32(val);
+    }
+#elif defined(__VXE__) || defined(__VXE2__)
+    for (; i + 3 < n; i += 4) {
+        float32x4_t val = vec_sub(vec_xl(0, x + i), vec_splats(mean));
+        vec_xst(val, 0, y + i);
+        val = vec_mul(val, val);
+        sum += (ggml_float)vec_hsum_f32x4(val);
+    }
+#endif
+    for (; i < n; ++i) {
+        float val = x[i] - mean;
+        val *= val;
+        sum += (ggml_float)val;
+        y[i] = val;
+    }
+    return sum/n;
+}
+
 ggml_float ggml_vec_soft_max_f32(const int n, float * y, const float * x, float max) {
     int i = 0;
     ggml_float sum = 0;

ggml/src/ggml-cpu/vec.h

@@ -44,6 +44,7 @@ void ggml_vec_dot_bf16(int n, float * GGML_RESTRICT s, size_t bs, ggml_bf16_t *
 void ggml_vec_dot_f16(int n, float * GGML_RESTRICT s, size_t bs, ggml_fp16_t * GGML_RESTRICT x, size_t bx, ggml_fp16_t * GGML_RESTRICT y, size_t by, int nrc);
 
 void ggml_vec_silu_f32(const int n, float * y, const float * x);
+ggml_float ggml_vec_cvar_f32(const int n, float * y, const float * x, const float mean); //it will also center y ( y = y - mean )
 ggml_float ggml_vec_soft_max_f32(const int n, float * y, const float * x, float max);
 ggml_float ggml_vec_log_soft_max_f32(const int n, float * y, const float * x, float max);
 

src/llama-kv-cache.cpp

@@ -123,11 +123,8 @@ llama_kv_cache::llama_kv_cache(
             throw std::runtime_error("failed to create ggml context for kv cache");
         }
 
-        ggml_tensor * k;
-        ggml_tensor * v;
-
-        k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
-        v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
+        ggml_tensor * k = ggml_new_tensor_3d(ctx, type_k, n_embd_k_gqa, kv_size, n_stream);
+        ggml_tensor * v = ggml_new_tensor_3d(ctx, type_v, n_embd_v_gqa, kv_size, n_stream);
 
         ggml_format_name(k, "cache_k_l%d", il);
         ggml_format_name(v, "cache_v_l%d", il);

src/llama-sampling.cpp

@@ -2541,8 +2541,13 @@ static void llama_sampler_infill_apply(struct llama_sampler * smpl, llama_token_
     if (n_non_eog == 0) {
         cur_p->size = 1;
         cur_p->data[0].id = ctx->vocab->token_eot();
+        if (cur_p->data[0].id == LLAMA_TOKEN_NULL) {
+            cur_p->data[0].id = ctx->vocab->token_eos();
+        }
         cur_p->data[0].logit = 1.0f;
 
+        GGML_ASSERT(cur_p->data[0].id != LLAMA_TOKEN_NULL);
+
         return;
     }
 

src/llama-vocab.cpp

@@ -2410,6 +2410,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                         || t.first == "<|end|>"
                         || t.first == "<end_of_turn>"
                         || t.first == "<|endoftext|>"
+                        || t.first == "<|end_of_text|>" // granite
                         || t.first == "<EOT>"
                         || t.first == "_<EOT>"
                         || t.first == "<｜end▁of▁sentence｜>" // DeepSeek

tools/server/tests/unit/test_basic.py

@@ -66,8 +66,7 @@ def test_server_slots():
     assert len(res.body) == server.n_slots
     assert server.n_ctx is not None and server.n_slots is not None
     assert res.body[0]["n_ctx"] == server.n_ctx / server.n_slots
-    assert "params" in res.body[0]
-    assert res.body[0]["params"]["seed"] == server.seed
+    assert "params" not in res.body[0]
 
 
 def test_load_split_model():

tools/server/tests/unit/test_chat_completion.py

@@ -19,8 +19,8 @@ def create_server():
         (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True,  None),
         (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'),
         (None, "Book", "What is the best book", 8, "^ blue",                    23, 8, "length", True, "This is not a chat template, it is"),
-        ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None),
-        ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None),
+        ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length", False, None),
+        ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length", True, None),
         (None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", False, None),
         (None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", True, None),
     ]
@@ -54,7 +54,7 @@ def test_chat_completion(model, system_prompt, user_prompt, max_tokens, re_conte
     "system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason",
     [
         ("Book", "What is the best book", 8, "(Suddenly)+", 77, 8, "length"),
-        ("You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length"),
+        ("You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 128, "length"),
     ]
 )
 def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason):
@@ -408,6 +408,28 @@ def test_context_size_exceeded():
     assert res.body["error"]["n_ctx"] == server.n_ctx // server.n_slots
 
 
+def test_context_size_exceeded_stream():
+    global server
+    server.start()
+    try:
+        for _ in server.make_stream_request("POST", "/chat/completions", data={
+            "messages": [
+                {"role": "system", "content": "Book"},
+                {"role": "user", "content": "What is the best book"},
+            ] * 100, # make the prompt too long
+            "stream": True}):
+                pass
+        assert False, "Should have failed"
+    except ServerError as e:
+        assert e.code == 400
+        assert "error" in e.body
+        assert e.body["error"]["type"] == "exceed_context_size_error"
+        assert e.body["error"]["n_prompt_tokens"] > 0
+        assert server.n_ctx is not None
+        assert server.n_slots is not None
+        assert e.body["error"]["n_ctx"] == server.n_ctx // server.n_slots
+
+
 @pytest.mark.parametrize(
     "n_batch,batch_count,reuse_cache",
     [

tools/server/tests/unit/test_completion.py

@@ -16,7 +16,7 @@ def create_server():
 
 @pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated,return_tokens", [
     ("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False, False),
-    ("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False, True),
+    ("Write a joke about AI from a very long prompt which will not be truncated", 64, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False, True),
 ])
 def test_completion(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool, return_tokens: bool):
     global server
@@ -41,7 +41,7 @@ def test_completion(prompt: str, n_predict: int, re_content: str, n_prompt: int,
 
 @pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated", [
     ("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False),
-    ("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False),
+    ("Write a joke about AI from a very long prompt which will not be truncated", 64, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False),
 ])
 def test_completion_stream(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool):
     global server

tools/server/tests/unit/test_ctx_shift.py

@@ -4,6 +4,12 @@ from utils import *
 server = ServerPreset.tinyllama2()
 
 
+SHORT_TEXT = """
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+""".strip()
+
 LONG_TEXT = """
 Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
 Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
@@ -21,19 +27,18 @@ def create_server():
 
 
 def test_ctx_shift_enabled():
-    # the prompt is 301 tokens
+    # the prompt is 226 tokens
     # the slot context is 512/2 = 256 tokens
-    # the prompt is truncated to keep the last (301 - 256/2) = 173 tokens
     # 96 tokens are generated thanks to shifting the context when it gets full
     global server
     server.enable_ctx_shift = True
     server.start()
     res = server.make_request("POST", "/completion", data={
         "n_predict": 96,
-        "prompt": LONG_TEXT,
+        "prompt": SHORT_TEXT,
     })
     assert res.status_code == 200
-    assert res.body["timings"]["prompt_n"] == 173
+    assert res.body["timings"]["prompt_n"] == 226
     assert res.body["timings"]["predicted_n"] == 96
     assert res.body["truncated"] is True
 

tools/server/tests/utils.py

@@ -35,6 +35,12 @@ class ServerResponse:
     body: dict | Any
 
 
+class ServerError(Exception):
+    def __init__(self, code, body):
+        self.code = code
+        self.body = body
+
+
 class ServerProcess:
     # default options
     debug: bool = False
@@ -297,6 +303,8 @@ class ServerProcess:
             response = requests.post(url, headers=headers, json=data, stream=True)
         else:
             raise ValueError(f"Unimplemented method: {method}")
+        if response.status_code != 200:
+            raise ServerError(response.status_code, response.json())
         for line_bytes in response.iter_lines():
             line = line_bytes.decode("utf-8")
             if '[DONE]' in line:

tools/server/utils.hpp

@@ -31,10 +31,10 @@
 
 using json = nlohmann::ordered_json;
 
-#define SLT_INF(slot, fmt, ...) LOG_INF("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
-#define SLT_WRN(slot, fmt, ...) LOG_WRN("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
-#define SLT_ERR(slot, fmt, ...) LOG_ERR("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
-#define SLT_DBG(slot, fmt, ...) LOG_DBG("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__)
+#define SLT_INF(slot, fmt, ...) LOG_INF("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, ((slot).task ? (slot).task->id : -1), __VA_ARGS__)
+#define SLT_WRN(slot, fmt, ...) LOG_WRN("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, ((slot).task ? (slot).task->id : -1), __VA_ARGS__)
+#define SLT_ERR(slot, fmt, ...) LOG_ERR("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, ((slot).task ? (slot).task->id : -1), __VA_ARGS__)
+#define SLT_DBG(slot, fmt, ...) LOG_DBG("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, ((slot).task ? (slot).task->id : -1), __VA_ARGS__)
 
 #define SRV_INF(fmt, ...) LOG_INF("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
 #define SRV_WRN(fmt, ...) LOG_WRN("srv  %12.*s: " fmt, 12, __func__, __VA_ARGS__)
@@ -1102,6 +1102,7 @@ public:
     ~server_tokens() = default;
 
     // Prevent copying
+    // TODO: server_tokens should be copyable - remove this:
     server_tokens(const server_tokens&) = delete;
     server_tokens& operator=(const server_tokens&) = delete;
 
@@ -1119,7 +1120,7 @@ public:
         }
     }
 
-    server_tokens(llama_tokens & tokens, bool has_mtmd) : has_mtmd(has_mtmd), tokens(tokens) {}
+    server_tokens(const llama_tokens & tokens, bool has_mtmd) : has_mtmd(has_mtmd), tokens(tokens) {}
 
     // for debugging
     std::string str() const {
@@ -1144,9 +1145,8 @@ public:
         auto it = map_pos_to_media.find(pos);
         if (it != map_pos_to_media.end()) {
             return it->second;
-        } else {
-            throw std::runtime_error("Chunk not found");
         }
+        throw std::runtime_error("Chunk not found");
     }
 
     void push_back(llama_token tok) {
@@ -1170,7 +1170,7 @@ public:
             map_pos_to_media[start_pos] = std::move(new_chunk);
         } else if (type == MTMD_INPUT_CHUNK_TYPE_TEXT) {
             size_t n_tokens;
-            auto text_tokens = mtmd_input_chunk_get_tokens_text(chunk, &n_tokens);
+            const auto * text_tokens = mtmd_input_chunk_get_tokens_text(chunk, &n_tokens);
             for (size_t i = 0; i < n_tokens; ++i) {
                 push_back(text_tokens[i]);
             }
@@ -1190,7 +1190,7 @@ public:
             // We could also just check, but this will prevent silently dropping MTMD data.
             GGML_ASSERT(has_mtmd);
             for (auto it = tokens.map_pos_to_media.begin(); it != tokens.map_pos_to_media.end(); ) {
-                auto chunk = tokens.map_pos_to_media[it->first].get();
+                auto * chunk = tokens.map_pos_to_media[it->first].get();
                 mtmd::input_chunk_ptr new_chunk(mtmd_input_chunk_copy(chunk));
                 map_pos_to_media[start_pos+it->first] = std::move(new_chunk);
             }
@@ -1271,33 +1271,52 @@ public:
     }
 
     size_t get_common_prefix(const server_tokens & b) const {
-        size_t max_idx = std::min(tokens.size(), b.tokens.size());
-        for (size_t i = 0; i < max_idx; ++i) {
-            auto & ai =   tokens[i];
-            auto & bi = b.tokens[i];
+        const size_t max_idx = std::min(tokens.size(), b.tokens.size());
 
-            if (ai == LLAMA_TOKEN_NULL && bi == LLAMA_TOKEN_NULL) {
-                GGML_ASSERT(has_mtmd);
-                const auto & a_chunk =   find_chunk(i);
-                const auto & b_chunk = b.find_chunk(i);
-                GGML_ASSERT(a_chunk && b_chunk);
-                std::string ai_id  = mtmd_input_chunk_get_id(a_chunk.get());
-                std::string bi_id  = mtmd_input_chunk_get_id(b_chunk.get());
-                size_t a_pos       = mtmd_input_chunk_get_n_pos(a_chunk.get());
-                size_t b_pos       = mtmd_input_chunk_get_n_pos(b_chunk.get());
-                if (ai_id == bi_id && a_pos == b_pos) {
-                    GGML_ASSERT(a_pos > 0 && "Invalid media chunk"); // should never happen
-                    i += a_pos - 1; // will be +1 by the for loop
+        if (!has_mtmd) {
+            for (size_t i = 0; i < max_idx; ++i) {
+                if (tokens[i] == b.tokens[i]) {
                     continue;
-                } else {
-                    return i;
                 }
-            } else if (ai == bi) {
-                continue;
-            } else {
+
                 return i;
             }
+
+            return max_idx;
         }
+
+        for (size_t i = 0; i < max_idx; ++i) {
+            const llama_token ai =   tokens[i];
+            const llama_token bi = b.tokens[i];
+
+            if (ai == LLAMA_TOKEN_NULL && bi == LLAMA_TOKEN_NULL) {
+                const auto & a_chunk =   find_chunk(i);
+                const auto & b_chunk = b.find_chunk(i);
+
+                GGML_ASSERT(a_chunk && b_chunk);
+
+                const std::string id_ai = mtmd_input_chunk_get_id(a_chunk.get());
+                const std::string id_bi = mtmd_input_chunk_get_id(b_chunk.get());
+
+                const size_t pos_a = mtmd_input_chunk_get_n_pos(a_chunk.get());
+                const size_t pos_b = mtmd_input_chunk_get_n_pos(b_chunk.get());
+
+                if (id_ai == id_bi && pos_a == pos_b) {
+                    GGML_ASSERT(pos_a > 0 && "Invalid media chunk"); // should never happen
+                    i += pos_a - 1; // will be +1 by the for loop
+                    continue;
+                }
+
+                return i;
+            }
+
+            if (ai == bi) {
+                continue;
+            }
+
+            return i;
+        }
+
         return max_idx; // all tokens are equal
     }
 
@@ -1308,7 +1327,7 @@ public:
         const int32_t n_vocab = llama_vocab_n_tokens(vocab);
 
         for (size_t i = 0; i < tokens.size(); ++i) {
-            auto & t = tokens[i];
+            const auto & t = tokens[i];
             if (t == LLAMA_TOKEN_NULL) {
                 try {
                     const auto & chunk = find_chunk(i);
@@ -1330,8 +1349,8 @@ public:
                 mtmd_context * mctx,
                 llama_pos n_past,
                 int32_t seq_id,
-                llama_pos & n_pos_out) {
-        auto & chunk = find_chunk(n_past);
+                llama_pos & n_pos_out) const {
+        const auto & chunk = find_chunk(n_past);
         const char * name = mtmd_input_chunk_get_type(chunk.get()) == MTMD_INPUT_CHUNK_TYPE_IMAGE
                             ? "image" : "audio";
         SRV_INF("processing %s...\n", name);

tools/server/webui/src/lib/services/chat.ts

@@ -122,9 +122,10 @@ export class ChatService {
 		requestBody.reasoning_format = currentConfig.disableReasoningFormat ? 'none' : 'auto';
 
 		if (temperature !== undefined) requestBody.temperature = temperature;
-		// Set max_tokens to -1 (infinite) if not provided or empty
-		requestBody.max_tokens =
-			max_tokens !== undefined && max_tokens !== null && max_tokens !== 0 ? max_tokens : -1;
+		if (max_tokens !== undefined) {
+			// Set max_tokens to -1 (infinite) when explicitly configured as 0 or null
+			requestBody.max_tokens = max_tokens !== null && max_tokens !== 0 ? max_tokens : -1;
+		}
 
 		if (dynatemp_range !== undefined) requestBody.dynatemp_range = dynatemp_range;
 		if (dynatemp_exponent !== undefined) requestBody.dynatemp_exponent = dynatemp_exponent;