Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/tools.sh
#	build-xcframework.sh
#	ci/run.sh
#	examples/Miku.sh
#	examples/chat-13B.sh
#	examples/chat-persistent.sh
#	examples/chat-vicuna.sh
#	examples/chat.sh
#	examples/jeopardy/jeopardy.sh
#	examples/reason-act.sh
#	examples/server-llama2-13B.sh
#	examples/sycl/build.sh
#	examples/sycl/run-llama2.sh
#	examples/sycl/run-llama3.sh
#	examples/ts-type-to-grammar.sh
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/apple/validate-apps.sh
#	scripts/apple/validate-ios.sh
#	scripts/apple/validate-macos.sh
#	scripts/apple/validate-tvos.sh
#	scripts/apple/validate-visionos.sh
#	scripts/check-requirements.sh
#	scripts/ci-run.sh
#	scripts/compare-commits.sh
#	scripts/debug-test.sh
#	scripts/gen-authors.sh
#	scripts/get-hellaswag.sh
#	scripts/get-pg.sh
#	scripts/get-wikitext-103.sh
#	scripts/get-wikitext-2.sh
#	scripts/get-winogrande.sh
#	scripts/hf.sh
#	scripts/qnt-all.sh
#	scripts/run-all-perf.sh
#	scripts/run-all-ppl.sh
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.sh
#	scripts/tool_bench.sh
#	tests/test-backend-ops.cpp
#	tests/test-lora-conversion-inference.sh
#	tests/test-tokenizer-0.sh
#	tools/server/README.md

tools/server/chat-llama2.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 API_URL="${API_URL:-http://127.0.0.1:8080}"
 

tools/server/chat.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 API_URL="${API_URL:-http://127.0.0.1:8080}"
 

tools/server/server.cpp

@@ -2110,6 +2110,7 @@ struct server_context {
             /* use_jinja             */ params_base.use_jinja,
             /* prefill_assistant     */ params_base.prefill_assistant,
             /* reasoning_format      */ params_base.reasoning_format,
+            /* chat_template_kwargs  */ params_base.default_template_kwargs,
             /* common_chat_templates */ chat_templates.get(),
             /* allow_image           */ mctx ? mtmd_support_vision(mctx) : false,
             /* allow_audio           */ mctx ? mtmd_support_audio (mctx) : false,

tools/server/tests/tests.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # make sure we are in the right directory
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )

tools/server/utils.hpp

@@ -579,6 +579,7 @@ struct oaicompat_parser_options {
     bool use_jinja;
     bool prefill_assistant;
     common_reasoning_format reasoning_format;
+    std::map<std::string,std::string> chat_template_kwargs;
     common_chat_templates * tmpls;
     bool allow_image;
     bool allow_audio;
@@ -756,6 +757,13 @@ static json oaicompat_chat_params_parse(
         llama_params["parse_tool_calls"] = true;
     }
 
+    // merge the template args provided from command line with the args provided in the user request
+    auto chat_template_kwargs_object = json_value(body, "chat_template_kwargs", json::object());
+    inputs.chat_template_kwargs = opt.chat_template_kwargs;
+    for (const auto & item : chat_template_kwargs_object.items()) {
+        inputs.chat_template_kwargs[item.key()] = item.value().dump();
+    }
+
     // if the assistant message appears at the end of list, we do not add end-of-turn token
     // for ex. this can be useful to modify the reasoning process in reasoning models
     bool prefill_assistant_message = !inputs.messages.empty() && inputs.messages.back().role == "assistant" && opt.prefill_assistant;
@@ -771,6 +779,11 @@ static json oaicompat_chat_params_parse(
 
         /* TODO: test this properly */
         inputs.reasoning_format = COMMON_REASONING_FORMAT_NONE;
+
+        if ( (!inputs.enable_thinking) || inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) {
+            throw std::runtime_error("Assistant response prefill is incompatible with enable_thinking.");
+        }
+
         inputs.add_generation_prompt = true;
     }
 

tools/server/webui/src/components/Sidebar.tsx

@@ -231,7 +231,7 @@ function ConversationItem({
       >
         {conv.name}
       </button>
-      <div className="dropdown dropdown-end h-5">
+      <div tabIndex={0} className="dropdown dropdown-end h-5">
         <BtnWithTooltips
           // on mobile, we always show the ellipsis icon
           // on desktop, we only show it when the user hovers over the conversation item