Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-and-test-snapdragon.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/server-webui.yml
#	.github/workflows/server.yml
#	.gitignore
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	grammars/README.md
#	scripts/snapdragon/qdc/run_qdc_jobs.py
#	scripts/snapdragon/qdc/tests/run_backend_ops_posix.py
#	scripts/snapdragon/qdc/tests/run_bench_tests_posix.py
#	scripts/snapdragon/qdc/tests/utils.py
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
#	tools/server/webui/src/lib/components/app/server/ServerLoadingSplash.svelte
#	tools/server/webui/src/routes/(chat)/chat/[id]/+page.svelte
#	ty.toml
This commit is contained in:
Concedo
2026-05-15 17:09:48 +08:00
parent 5962bca463 91e84fed64
commit da2cc90723
24 changed files with 444 additions and 13525 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/public/bundle.css
-1
View File
File diff suppressed because one or more lines are too long
tools/server/public/bundle.js
-13291
View File
File diff suppressed because it is too large Load Diff
tools/server/public/index.html
-34
View File
File diff suppressed because one or more lines are too long
tools/server/public/loading.html
-12
View File
@@ -1,12 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="refresh" content="5">
</head>
<body>
<div id="loading">
The model is loading. Please wait.<br/>
The user interface will appear soon.
</div>
</body>
</html>
tools/server/server-chat.cpp
+8 -3
View File
@@ -257,8 +257,11 @@ json server_chat_convert_responses_to_chatcmpl(const json & response_body) {
for (json resp_tool : response_body.at("tools")) {
json chatcmpl_tool;
if (json_value(resp_tool, "type", std::string()) != "function") {
throw std::invalid_argument("'type' of tool must be 'function'");
const std::string type = json_value(resp_tool, "type", std::string());
if (type != "function") {
// Non-function Responses tools have no Chat Completions equivalent.
SRV_WRN("unsupported Responses tool type '%s' skipped\n", type.c_str());
continue;
}
resp_tool.erase("type");
chatcmpl_tool["type"] = "function";
@@ -270,7 +273,9 @@ json server_chat_convert_responses_to_chatcmpl(const json & response_body) {
chatcmpl_tools.push_back(chatcmpl_tool);
}
chatcmpl_body.erase("tools");
chatcmpl_body["tools"] = chatcmpl_tools;
if (!chatcmpl_tools.empty()) {
chatcmpl_body["tools"] = chatcmpl_tools;
}
}
if (response_body.contains("max_output_tokens")) {
tools/server/server-http.cpp
+17 -17
View File
@@ -238,30 +238,30 @@ bool server_http_context::init(const common_params & params) {
};
auto middleware_server_state = [this](const httplib::Request & req, httplib::Response & res) {
(void)req; // suppress unused parameter warning when LLAMA_BUILD_WEBUI is not defined
bool ready = is_ready.load();
if (!ready) {
#ifdef LLAMA_BUILD_WEBUI
auto tmp = string_split<std::string>(req.path, '.');
if (req.path == "/" || tmp.back() == "html") {
if (req.path == "/" || (tmp.size() > 0 && tmp.back() == "html")) {
res.status = 503;
res.set_content(reinterpret_cast<const char*>(loading_html), loading_html_len, "text/html; charset=utf-8");
} else
#endif
{
// no endpoints is allowed to be accessed when the server is not ready
// this is to prevent any data races or inconsistent states
res.status = 503;
res.set_content(
safe_json_to_str(json {
{"error", {
{"message", "Loading model"},
{"type", "unavailable_error"},
{"code", 503}
}}
}),
"application/json; charset=utf-8"
);
return false;
}
#endif
// no endpoints are allowed to be accessed when the server is not ready
// this is to prevent any data races or inconsistent states
res.status = 503;
res.set_content(
safe_json_to_str(json {
{"error", {
{"message", "Loading model"},
{"type", "unavailable_error"},
{"code", 503}
}}
}),
"application/json; charset=utf-8"
);
return false;
}
return true;
tools/server/webui/README.md
+2 -2
View File
@@ -1,6 +1,6 @@
# llama.cpp Web UI
# llama-ui
A modern, feature-rich web interface for llama.cpp built with SvelteKit. This UI provides an intuitive chat interface with advanced file handling, conversation management, and comprehensive model interaction capabilities.
A modern, feature-rich web interface for llama-server built with SvelteKit. This UI provides an intuitive chat interface with advanced file handling, conversation management, and comprehensive model interaction capabilities.
The WebUI supports two server operation modes:
tools/server/webui/package-lock.json
Generated
+2 -2
View File
@@ -1,11 +1,11 @@
{
"name": "llama-server-webui",
"name": "llama-ui",
"version": "1.0.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "llama-server-webui",
"name": "llama-ui",
"version": "1.0.0",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.25.1",
tools/server/webui/package.json
+1 -1
View File
@@ -1,5 +1,5 @@
{
"name": "llama-server-webui",
"name": "llama-ui",
"private": true,
"version": "1.0.0",
"type": "module",
tools/server/webui/scripts/dev.sh
+4 -4
View File
@@ -1,7 +1,7 @@
#!/bin/bash
# Development script for llama.cpp webui
#
# Development script for llama-ui
#
# This script starts the webui development servers (Storybook and Vite).
# Note: You need to start llama-server separately.
#
@@ -14,12 +14,12 @@ cd ../../../
# Check and install git hooks if missing
check_and_install_hooks() {
local hooks_missing=false
# Check for required hooks
if [ ! -f ".git/hooks/pre-commit" ] || [ ! -f ".git/hooks/pre-push" ] || [ ! -f ".git/hooks/post-push" ]; then
hooks_missing=true
fi
if [ "$hooks_missing" = true ]; then
echo "🔧 Git hooks missing, installing them..."
cd tools/server/webui
tools/server/webui/scripts/install-git-hooks.sh
+3 -7
View File
@@ -1,7 +1,7 @@
#!/bin/bash
# Script to install pre-commit hook for webui
# Pre-commit: formats, checks, builds, and stages build output
# Pre-commit: formats, checks, and builds webui
REPO_ROOT=$(git rev-parse --show-toplevel)
PRE_COMMIT_HOOK="$REPO_ROOT/.git/hooks/pre-commit"
@@ -56,11 +56,7 @@ if git diff --cached --name-only | grep -q "^tools/server/webui/"; then
exit 1
fi
# Stage the build output alongside the source changes
cd "$REPO_ROOT"
git add tools/server/public/
echo "✅ Webui built and build output staged"
echo "✅ Webui built successfully"
fi
exit 0
@@ -75,7 +71,7 @@ if [ $? -eq 0 ]; then
echo ""
echo "The hook will automatically:"
echo " • Format, lint and check webui code before commits"
echo " • Build webui and stage tools/server/public/ into the same commit"
echo " • Build webui"
else
echo "❌ Failed to make hook executable"
exit 1
tools/server/webui/src/lib/components/app/server/ServerLoadingSplash.svelte
+1 -2
View File
@@ -8,8 +8,7 @@
message?: string;
}
let { class: className = '', message = 'Initializing connection to KoboldCpp server...' }: Props =
$props();
let { class: className = '', message = 'Initializing connection to server...' }: Props = $props();
</script>
<div class="flex h-full items-center justify-center {className}">
tools/server/webui/src/lib/constants/ui.ts
+1 -1
View File
@@ -5,7 +5,7 @@ import { ROUTES } from './routes';
export const FORK_TREE_DEPTH_PADDING = 8;
export const SYSTEM_MESSAGE_PLACEHOLDER = 'System message';
export const APP_NAME = import.meta.env.VITE_PUBLIC_APP_NAME || 'llama.cpp';
export const APP_NAME = import.meta.env.VITE_PUBLIC_APP_NAME || 'llama-ui';
export const ICON_STRIP_TRANSITION_DURATION = 150;
export const ICON_STRIP_TRANSITION_DELAY_MULTIPLIER = 50;
tools/server/webui/src/lib/services/chat.service.ts
+1 -1
View File
@@ -76,7 +76,7 @@ export class ChatService {
*/
/**
* Sends a chat completion request to the llama.cpp server.
* Sends a chat completion request to the llama-server.
* Supports both streaming and non-streaming responses with comprehensive parameter configuration.
* Automatically converts database messages with attachments to the appropriate API format.
*
tools/server/webui/src/routes/(chat)/chat/[id]/+page.svelte
+2 -2
View File
@@ -3,7 +3,7 @@
import { page } from '$app/state';
import { afterNavigate } from '$app/navigation';
import { DialogModelNotAvailable } from '$lib/components/app';
import { ROUTES } from '$lib/constants/routes';
import { APP_NAME, ROUTES } from '$lib/constants';
import { chatStore, isLoading } from '$lib/stores/chat.svelte';
import { conversationsStore, activeConversation } from '$lib/stores/conversations.svelte';
import { modelsStore, modelOptions } from '$lib/stores/models.svelte';
@@ -125,7 +125,7 @@
</script>
<svelte:head>
<title>{activeConversation()?.name || 'Chat'} - llama.cpp UI (KoboldCpp Backend)</title>
<title>{activeConversation()?.name || 'Chat'} - {APP_NAME}</title>
</svelte:head>
<DialogModelNotAvailable
tools/server/webui/svelte.config.js
+1 -1
View File
@@ -28,7 +28,7 @@ const config = {
$styles: 'src/styles'
},
version: {
name: 'llama-server-webui'
name: 'llama-ui'
}
},
tools/server/webui/tests/stories/Introduction.mdx
+2 -2
View File
@@ -4,11 +4,11 @@ import { Meta } from '@storybook/addon-docs/blocks';
# llama.cpp Web UI
Welcome to the **llama.cpp Web UI** component library! This Storybook showcases the components used in the modern web interface for the llama.cpp server.
Welcome to the **llama-ui** component library! This Storybook showcases the components used in the modern web interface for the llama-server.
## 🚀 About This Project
WebUI is a modern web interface for the llama.cpp server, built with SvelteKit and ShadCN UI. Features include:
WebUI is a modern web interface for the llama-server, built with SvelteKit and ShadCN UI. Features include:
- **Real-time chat conversations** with AI assistants
- **Multi-conversation management** with persistent storage
tools/server/webui/vite.config.ts
-5
View File
@@ -23,11 +23,6 @@ export default defineConfig({
minify: true
},
esbuild: {
lineLimit: 500,
minifyIdentifiers: false
},
css: {
preprocessorOptions: {
scss: {