cont : remove /api/tags

* llama: fix crash in print_info for GLM-DSA when vocab_only is set

* addressed code review comments

* cont : simplify

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

src/llama-model.cpp

@@ -8180,114 +8180,114 @@ void llama_model::print_info() const {
             LLAMA_LOG_INFO("%s: n_cls_out             = %u\n", __func__, hparams.n_cls_out);
 
             size_t i = 0;
-            for (auto label : classifier_labels) {
+            for (const auto & label : classifier_labels) {
                 LLAMA_LOG_INFO("%s: cls_label[%2zu]         = %s\n", __func__, i++, label.c_str());
             }
         }
-    }
 
-    if (arch == LLM_ARCH_MAMBA ||
-        arch == LLM_ARCH_MAMBA2 ||
-        arch == LLM_ARCH_JAMBA ||
-        arch == LLM_ARCH_FALCON_H1 ||
-        arch == LLM_ARCH_PLAMO2 ||
-        arch == LLM_ARCH_GRANITE_HYBRID ||
-        arch == LLM_ARCH_QWEN3NEXT ||
-        arch == LLM_ARCH_QWEN35 ||
-        arch == LLM_ARCH_QWEN35MOE ||
-        arch == LLM_ARCH_NEMOTRON_H ||
-        arch == LLM_ARCH_NEMOTRON_H_MOE) {
-        LLAMA_LOG_INFO("%s: ssm_d_conv            = %u\n",     __func__, hparams.ssm_d_conv);
-        LLAMA_LOG_INFO("%s: ssm_d_inner           = %u\n",     __func__, hparams.ssm_d_inner);
-        LLAMA_LOG_INFO("%s: ssm_d_state           = %u\n",     __func__, hparams.ssm_d_state);
-        LLAMA_LOG_INFO("%s: ssm_dt_rank           = %u\n",     __func__, hparams.ssm_dt_rank);
-        LLAMA_LOG_INFO("%s: ssm_n_group           = %u\n",     __func__, hparams.ssm_n_group);
-        LLAMA_LOG_INFO("%s: ssm_dt_b_c_rms        = %d\n",     __func__, hparams.ssm_dt_b_c_rms);
-    }
+        if (arch == LLM_ARCH_MAMBA ||
+                arch == LLM_ARCH_MAMBA2 ||
+                arch == LLM_ARCH_JAMBA ||
+                arch == LLM_ARCH_FALCON_H1 ||
+                arch == LLM_ARCH_PLAMO2 ||
+                arch == LLM_ARCH_GRANITE_HYBRID ||
+                arch == LLM_ARCH_QWEN3NEXT ||
+                arch == LLM_ARCH_QWEN35 ||
+                arch == LLM_ARCH_QWEN35MOE ||
+                arch == LLM_ARCH_NEMOTRON_H ||
+                arch == LLM_ARCH_NEMOTRON_H_MOE) {
+            LLAMA_LOG_INFO("%s: ssm_d_conv            = %u\n",     __func__, hparams.ssm_d_conv);
+            LLAMA_LOG_INFO("%s: ssm_d_inner           = %u\n",     __func__, hparams.ssm_d_inner);
+            LLAMA_LOG_INFO("%s: ssm_d_state           = %u\n",     __func__, hparams.ssm_d_state);
+            LLAMA_LOG_INFO("%s: ssm_dt_rank           = %u\n",     __func__, hparams.ssm_dt_rank);
+            LLAMA_LOG_INFO("%s: ssm_n_group           = %u\n",     __func__, hparams.ssm_n_group);
+            LLAMA_LOG_INFO("%s: ssm_dt_b_c_rms        = %d\n",     __func__, hparams.ssm_dt_b_c_rms);
+        }
 
-    LLAMA_LOG_INFO("%s: model type            = %s\n",     __func__, type_name().c_str());
-    if (pimpl->n_elements >= 1e12) {
-        LLAMA_LOG_INFO("%s: model params          = %.2f T\n", __func__, pimpl->n_elements*1e-12);
-    } else if (pimpl->n_elements >= 1e9) {
-        LLAMA_LOG_INFO("%s: model params          = %.2f B\n", __func__, pimpl->n_elements*1e-9);
-    } else if (pimpl->n_elements >= 1e6) {
-        LLAMA_LOG_INFO("%s: model params          = %.2f M\n", __func__, pimpl->n_elements*1e-6);
-    } else {
-        LLAMA_LOG_INFO("%s: model params          = %.2f K\n", __func__, pimpl->n_elements*1e-3);
-    }
+        LLAMA_LOG_INFO("%s: model type            = %s\n",     __func__, type_name().c_str());
+        if (pimpl->n_elements >= 1e12) {
+            LLAMA_LOG_INFO("%s: model params          = %.2f T\n", __func__, pimpl->n_elements*1e-12);
+        } else if (pimpl->n_elements >= 1e9) {
+            LLAMA_LOG_INFO("%s: model params          = %.2f B\n", __func__, pimpl->n_elements*1e-9);
+        } else if (pimpl->n_elements >= 1e6) {
+            LLAMA_LOG_INFO("%s: model params          = %.2f M\n", __func__, pimpl->n_elements*1e-6);
+        } else {
+            LLAMA_LOG_INFO("%s: model params          = %.2f K\n", __func__, pimpl->n_elements*1e-3);
+        }
 
-    // general kv
-    LLAMA_LOG_INFO("%s: general.name          = %s\n",    __func__, name.c_str());
+        // general kv
+        LLAMA_LOG_INFO("%s: general.name          = %s\n",    __func__, name.c_str());
 
-    if (arch == LLM_ARCH_DEEPSEEK) {
-        LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
-        LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
-    }
+        if (arch == LLM_ARCH_DEEPSEEK) {
+            LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
+            LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
+        }
 
-    if (arch == LLM_ARCH_DEEPSEEK2 || arch == LLM_ARCH_DEEPSEEK2OCR || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_MISTRAL4) {
-        LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
-        LLAMA_LOG_INFO("%s: n_lora_q              = %d\n",     __func__, hparams.n_lora_q);
-        LLAMA_LOG_INFO("%s: n_lora_kv             = %d\n",     __func__, hparams.n_lora_kv);
-        LLAMA_LOG_INFO("%s: n_embd_head_k_mla     = %d\n",     __func__, hparams.n_embd_head_k_mla());
-        LLAMA_LOG_INFO("%s: n_embd_head_v_mla     = %d\n",     __func__, hparams.n_embd_head_v_mla());
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
-        LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
-        LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
-        LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
-    }
+        if (arch == LLM_ARCH_DEEPSEEK2 || arch == LLM_ARCH_DEEPSEEK2OCR || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_MISTRAL4) {
+            LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
+            LLAMA_LOG_INFO("%s: n_lora_q              = %d\n",     __func__, hparams.n_lora_q);
+            LLAMA_LOG_INFO("%s: n_lora_kv             = %d\n",     __func__, hparams.n_lora_kv);
+            LLAMA_LOG_INFO("%s: n_embd_head_k_mla     = %d\n",     __func__, hparams.n_embd_head_k_mla());
+            LLAMA_LOG_INFO("%s: n_embd_head_v_mla     = %d\n",     __func__, hparams.n_embd_head_v_mla());
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
+            LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
+            LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
+            LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
+        }
 
-    if (arch == LLM_ARCH_QWEN2MOE) {
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n",     __func__, hparams.n_ff_shexp);
-    }
+        if (arch == LLM_ARCH_QWEN2MOE) {
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n",     __func__, hparams.n_ff_shexp);
+        }
 
-    if (arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE || arch == LLM_ARCH_RND1) {
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-    }
+        if (arch == LLM_ARCH_QWEN3MOE || arch == LLM_ARCH_OPENAI_MOE || arch == LLM_ARCH_QWEN3VLMOE || arch == LLM_ARCH_RND1) {
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+        }
 
-    if (arch == LLM_ARCH_MINICPM ||
-        arch == LLM_ARCH_GRANITE ||
-        arch == LLM_ARCH_GRANITE_MOE ||
-        arch == LLM_ARCH_GRANITE_HYBRID ||
-        arch == LLM_ARCH_NEMOTRON_H_MOE) {
-        LLAMA_LOG_INFO("%s: f_embedding_scale     = %f\n", __func__, hparams.f_embedding_scale);
-        LLAMA_LOG_INFO("%s: f_residual_scale      = %f\n", __func__, hparams.f_residual_scale);
-        LLAMA_LOG_INFO("%s: f_attention_scale     = %f\n", __func__, hparams.f_attention_scale);
-        LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n", __func__, hparams.n_ff_shexp);
-    }
+        if (arch == LLM_ARCH_MINICPM ||
+                arch == LLM_ARCH_GRANITE ||
+                arch == LLM_ARCH_GRANITE_MOE ||
+                arch == LLM_ARCH_GRANITE_HYBRID ||
+                arch == LLM_ARCH_NEMOTRON_H_MOE) {
+            LLAMA_LOG_INFO("%s: f_embedding_scale     = %f\n", __func__, hparams.f_embedding_scale);
+            LLAMA_LOG_INFO("%s: f_residual_scale      = %f\n", __func__, hparams.f_residual_scale);
+            LLAMA_LOG_INFO("%s: f_attention_scale     = %f\n", __func__, hparams.f_attention_scale);
+            LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n", __func__, hparams.n_ff_shexp);
+        }
 
-    if (arch == LLM_ARCH_BAILINGMOE) {
-        LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
-        LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
-        LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
-    }
+        if (arch == LLM_ARCH_BAILINGMOE) {
+            LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
+            LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
+            LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
+        }
 
-    if (arch == LLM_ARCH_BAILINGMOE2) {
-        LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n",     __func__, hparams.n_ff_shexp);
-        LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
-        LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
-        LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
-        LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
-        LLAMA_LOG_INFO("%s: nextn_predict_layers  = %d\n",     __func__, hparams.nextn_predict_layers);
-    }
+        if (arch == LLM_ARCH_BAILINGMOE2) {
+            LLAMA_LOG_INFO("%s: n_layer_dense_lead    = %d\n",     __func__, hparams.n_layer_dense_lead);
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_ff_shexp            = %d\n",     __func__, hparams.n_ff_shexp);
+            LLAMA_LOG_INFO("%s: n_expert_shared       = %d\n",     __func__, hparams.n_expert_shared);
+            LLAMA_LOG_INFO("%s: expert_weights_scale  = %.1f\n",   __func__, hparams.expert_weights_scale);
+            LLAMA_LOG_INFO("%s: expert_weights_norm   = %d\n",     __func__, hparams.expert_weights_norm);
+            LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
+            LLAMA_LOG_INFO("%s: nextn_predict_layers  = %d\n",     __func__, hparams.nextn_predict_layers);
+        }
 
-    if (arch == LLM_ARCH_SMALLTHINKER || arch == LLM_ARCH_LFM2MOE) {
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
-    }
+        if (arch == LLM_ARCH_SMALLTHINKER || arch == LLM_ARCH_LFM2MOE) {
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: expert_gating_func    = %s\n",     __func__, llama_expert_gating_func_name((llama_expert_gating_func_type) hparams.expert_gating_func));
+        }
 
-    if (arch == LLM_ARCH_GROVEMOE) {
-        LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
-        LLAMA_LOG_INFO("%s: n_ff_chexp            = %d\n",     __func__, hparams.n_ff_chexp);
-        LLAMA_LOG_INFO("%s: n_group_experts       = %d\n",     __func__, hparams.n_group_experts);
-        LLAMA_LOG_INFO("%s: expert_group_scale    = %.2f\n",   __func__, hparams.expert_group_scale);
+        if (arch == LLM_ARCH_GROVEMOE) {
+            LLAMA_LOG_INFO("%s: n_ff_exp              = %d\n",     __func__, hparams.n_ff_exp);
+            LLAMA_LOG_INFO("%s: n_ff_chexp            = %d\n",     __func__, hparams.n_ff_chexp);
+            LLAMA_LOG_INFO("%s: n_group_experts       = %d\n",     __func__, hparams.n_group_experts);
+            LLAMA_LOG_INFO("%s: expert_group_scale    = %.2f\n",   __func__, hparams.expert_group_scale);
+        }
     }
 
     vocab.print_info();

tools/server/server-context.cpp

@@ -3653,34 +3653,6 @@ void server_routes::init_routes() {
         return res;
     };
 
-    this->get_api_show = [this](const server_http_req &) {
-        auto res = create_response();
-        std::string tmpl_default = common_chat_templates_source(meta->chat_params.tmpls.get(), "");
-        json data = {
-            {
-                "model_info", {
-                    { "llama.context_length", meta->slot_n_ctx },
-                }
-            },
-            {"modelfile", ""},
-            {"parameters", ""},
-            {"template", tmpl_default},
-            {"details", {
-                {"parent_model", ""},
-                {"format", "gguf"},
-                {"family", ""},
-                {"families", {""}},
-                {"parameter_size", ""},
-                {"quantization_level", ""}
-            }},
-            {"model_info", ""},
-            {"capabilities", meta->has_mtmd ? json({"completion","multimodal"}) : json({"completion"})}
-        };
-
-        res->ok(data);
-        return res;
-    };
-
     this->post_infill = [this](const server_http_req & req) {
         auto res = create_response();
         // check model compatibility

tools/server/server-context.h

@@ -105,7 +105,6 @@ struct server_routes {
     server_http_context::handler_t post_slots;
     server_http_context::handler_t get_props;
     server_http_context::handler_t post_props;
-    server_http_context::handler_t get_api_show;
     server_http_context::handler_t post_infill;
     server_http_context::handler_t post_completions;
     server_http_context::handler_t post_completions_oai;

tools/server/server-http.cpp

@@ -143,7 +143,6 @@ bool server_http_context::init(const common_params & params) {
             "/v1/health",
             "/models",
             "/v1/models",
-            "/api/tags",
             "/",
             "/index.html",
             "/bundle.js",

tools/server/server.cpp

@@ -141,7 +141,6 @@ int main(int argc, char ** argv) {
         // note: routes.get_health stays the same
         routes.get_metrics                 = models_routes->proxy_get;
         routes.post_props                  = models_routes->proxy_post;
-        routes.get_api_show                = models_routes->proxy_get;
         routes.post_completions            = models_routes->proxy_post;
         routes.post_completions_oai        = models_routes->proxy_post;
         routes.post_chat_completions       = models_routes->proxy_post;
@@ -174,16 +173,13 @@ int main(int argc, char ** argv) {
     ctx_http.get ("/metrics",                  ex_wrapper(routes.get_metrics));
     ctx_http.get ("/props",                    ex_wrapper(routes.get_props));
     ctx_http.post("/props",                    ex_wrapper(routes.post_props));
-    ctx_http.post("/api/show",                 ex_wrapper(routes.get_api_show));
     ctx_http.get ("/models",                   ex_wrapper(routes.get_models)); // public endpoint (no API key check)
     ctx_http.get ("/v1/models",                ex_wrapper(routes.get_models)); // public endpoint (no API key check)
-    ctx_http.get ("/api/tags",                 ex_wrapper(routes.get_models)); // ollama specific endpoint. public endpoint (no API key check)
     ctx_http.post("/completion",               ex_wrapper(routes.post_completions)); // legacy
     ctx_http.post("/completions",              ex_wrapper(routes.post_completions));
     ctx_http.post("/v1/completions",           ex_wrapper(routes.post_completions_oai));
     ctx_http.post("/chat/completions",         ex_wrapper(routes.post_chat_completions));
     ctx_http.post("/v1/chat/completions",      ex_wrapper(routes.post_chat_completions));
-    ctx_http.post("/api/chat",                 ex_wrapper(routes.post_chat_completions)); // ollama specific endpoint
     ctx_http.post("/v1/responses",             ex_wrapper(routes.post_responses_oai));
     ctx_http.post("/responses",                ex_wrapper(routes.post_responses_oai));
     ctx_http.post("/v1/audio/transcriptions",  ex_wrapper(routes.post_transcriptions_oai));