ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064)

* webui: Move static build output from `tools/server/public` to `build/ui` directory

* refactor: Move to `tools/ui`

* refactor: rename CMake variables and preprocessor defines

- Rename LLAMA_BUILD_WEBUI -> LLAMA_BUILD_UI (old kept as deprecated)
- Rename LLAMA_USE_PREBUILT_WEBUI -> LLAMA_USE_PREBUILT_UI (old kept as deprecated)
- Backward compat: old vars auto-forward to new ones with DEPRECATION warning
- Rename internal vars: WEBUI_SOURCE -> UI_SOURCE, WEBUI_SOURCE_DIR -> UI_SOURCE_DIR, etc.
- Rename HF bucket: LLAMA_WEBUI_HF_BUCKET -> LLAMA_UI_HF_BUCKET
- Emit both LLAMA_BUILD_WEBUI and LLAMA_BUILD_UI preprocessor defines
- Emit both LLAMA_WEBUI_DEFAULT_ENABLED and LLAMA_UI_DEFAULT_ENABLED

* refactor: rename CLI flags (--webui -> --ui) with backward compat

- Add --ui/--no-ui (old --webui/--no-webui kept as deprecated aliases)
- Add --ui-config (old --webui-config kept as deprecated alias)
- Add --ui-config-file (old --webui-config-file kept as deprecated alias)
- Add --ui-mcp-proxy/--no-ui-mcp-proxy (old --webui-mcp-proxy kept as deprecated)
- Add new env vars: LLAMA_ARG_UI, LLAMA_ARG_UI_CONFIG, LLAMA_ARG_UI_CONFIG_FILE, LLAMA_ARG_UI_MCP_PROXY
- C++ struct fields: params.ui, params.ui_config_json, params.ui_mcp_proxy added alongside old fields
- Backward compat: old fields synced to new ones in g_params_to_internals

* refactor: update C++ server internals with backward compat

- Rename json_webui_settings -> json_ui_settings (both kept in server_context_meta)
- Rename params.webui usage -> params.ui (both synced, old still works)
- JSON API emits both "ui"/"ui_settings" and "webui"/"webui_settings" keys
- Server routes use params.ui_mcp_proxy || params.webui_mcp_proxy
- Preprocessor guards use #if defined(LLAMA_BUILD_UI) || defined(LLAMA_BUILD_WEBUI)

* refactor: rename CI/CD workflows, artifacts, and build script

- Rename webui-build.yml -> ui-build.yml; artifact webui-build -> ui-build
- Rename webui-publish.yml -> ui-publish.yml; var HF_BUCKET_WEBUI_STATIC_OUTPUT -> HF_BUCKET_UI_STATIC_OUTPUT
- Rename server-webui.yml -> server-ui.yml; job webui-build/checks -> ui-build/checks
- Update server.yml: job/artifact refs webui-build -> ui-build
- Update release.yml: all webui-build/publish refs -> ui-build/publish; HF_TOKEN_WEBUI_STATIC_OUTPUT -> HF_TOKEN_UI_STATIC_OUTPUT
- Update server-self-hosted.yml: webui-build -> ui-build
- Update build-self-hosted.yml: HF_WEBUI_VERSION -> HF_UI_VERSION
- Rename webui-download.cmake -> ui-download.cmake (internal refs updated)
- Update labeler.yml: server/webui -> server/ui path label

* docs: update CODEOWNERS and server README docs

- Update CODEOWNERS: team ggml-org/llama-webui -> ggml-org/llama-ui, path /tools/server/webui/ -> /tools/ui/
- Update server README.md: CLI tables show --ui flags with deprecated --webui aliases
- Update server README-dev.md: "WebUI" -> "UI", paths updated to tools/ui/

* fix: Small fixes for UI build

* fix: CMake.txt syntax

* chore: Formatting

* fix: `.editorconfig` for llama-ui

* chore: Formatting

* refactor: Use `APP_NAME` in Error route

* refactor: Cleanup

* refactor: Single migration service

* make llama-ui a linkable target

* fix: UI Build output

* fix: Missing change

* fix: separate llama-ui npm build output into build/tools/ui/dist subfolder + use cmake npm build instead of downloading ui-build.yml artifacts in CI

* refactor: UI workflows cleanup

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Aleksander Grygier
2026-05-16 02:02:40 +02:00
committed by GitHub
co-authored by Xuan Son Nguyen
parent 49d1701bd2
commit 59778f0196
565 changed files with 1610 additions and 694 deletions
@@ -0,0 +1,270 @@
<script lang="ts">
import * as Dialog from '$lib/components/ui/dialog';
import * as Table from '$lib/components/ui/table';
import { BadgesModality, ActionIconCopyToClipboard } from '$lib/components/app';
import { serverStore } from '$lib/stores/server.svelte';
import { modelsStore, modelOptions, modelsLoading } from '$lib/stores/models.svelte';
import { formatFileSize, formatParameters, formatNumber } from '$lib/utils';
import type { ApiLlamaCppServerProps } from '$lib/types';
interface Props {
open?: boolean;
onOpenChange?: (open: boolean) => void;
// when set, fetch props from the child process (router mode)
modelId?: string | null;
}
let { open = $bindable(), onOpenChange, modelId = null }: Props = $props();
let isRouter = $derived(serverStore.isRouterMode);
// per-model props fetched from the child process
let routerModelProps = $state<ApiLlamaCppServerProps | null>(null);
let isLoadingRouterProps = $state(false);
// in router mode use per-model props, otherwise use global props
let serverProps = $derived(isRouter && modelId ? routerModelProps : serverStore.props);
let modelName = $derived(isRouter && modelId ? modelId : modelsStore.singleModelName);
let models = $derived(modelOptions());
let isLoadingModels = $derived(modelsLoading());
// in router mode, find the model option matching modelId
// in single mode, use the first model as before
let firstModel = $derived.by(() => {
if (isRouter && modelId) {
return models.find((m) => m.model === modelId) ?? null;
}
return models[0] ?? null;
});
// Get modalities from modelStore using the model ID from the first model
let modalities = $derived.by(() => {
if (!firstModel?.id) return [];
return modelsStore.getModelModalitiesArray(firstModel.id);
});
// Ensure models are fetched when dialog opens
$effect(() => {
if (open && models.length === 0) {
modelsStore.fetch();
}
});
// fetch per-model props from child process when dialog opens in router mode
$effect(() => {
if (open && isRouter && modelId) {
isLoadingRouterProps = true;
modelsStore
.fetchModelProps(modelId)
.then((props) => {
routerModelProps = props;
})
.catch(() => {
routerModelProps = null;
})
.finally(() => {
isLoadingRouterProps = false;
});
}
if (!open) {
routerModelProps = null;
}
});
</script>
<Dialog.Root bind:open {onOpenChange}>
<Dialog.Content class="@container z-9999 !max-h-[80dvh] !max-w-[60rem] max-w-full">
<style>
@container (max-width: 56rem) {
.resizable-text-container {
max-width: calc(100vw - var(--threshold));
}
}
</style>
<Dialog.Header>
<Dialog.Title>Model Information</Dialog.Title>
<Dialog.Description>Current model details and capabilities</Dialog.Description>
</Dialog.Header>
<div class="space-y-6 py-4">
{#if isLoadingModels || isLoadingRouterProps}
<div class="flex items-center justify-center py-8">
<div class="text-sm text-muted-foreground">Loading model information...</div>
</div>
{:else if firstModel}
{@const modelMeta = firstModel.meta}
{#if serverProps}
<Table.Root>
<Table.Header>
<Table.Row>
<Table.Head class="w-[10rem]">Model</Table.Head>
<Table.Head>
<div class="inline-flex items-center gap-2">
<span
class="resizable-text-container min-w-0 flex-1 truncate"
style:--threshold="12rem"
>
{modelName}
</span>
<ActionIconCopyToClipboard
text={modelName || ''}
canCopy={!!modelName}
ariaLabel="Copy model name to clipboard"
/>
</div>
</Table.Head>
</Table.Row>
</Table.Header>
<Table.Body>
<!-- Model Path -->
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium">File Path</Table.Cell>
<Table.Cell
class="inline-flex h-10 items-center gap-2 align-middle font-mono text-xs"
>
<span
class="resizable-text-container min-w-0 flex-1 truncate"
style:--threshold="14rem"
>
{serverProps.model_path}
</span>
<ActionIconCopyToClipboard
text={serverProps.model_path}
ariaLabel="Copy model path to clipboard"
/>
</Table.Cell>
</Table.Row>
<!-- Context Size -->
{#if serverProps?.default_generation_settings?.n_ctx}
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium">Context Size</Table.Cell>
<Table.Cell
>{formatNumber(serverProps.default_generation_settings.n_ctx)} tokens</Table.Cell
>
</Table.Row>
{:else}
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium text-red-500"
>Context Size</Table.Cell
>
<Table.Cell class="text-red-500">Not available</Table.Cell>
</Table.Row>
{/if}
<!-- Training Context -->
{#if modelMeta?.n_ctx_train}
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium">Training Context</Table.Cell>
<Table.Cell>{formatNumber(modelMeta.n_ctx_train)} tokens</Table.Cell>
</Table.Row>
{/if}
<!-- Model Size -->
{#if modelMeta?.size}
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium">Model Size</Table.Cell>
<Table.Cell>{formatFileSize(modelMeta.size)}</Table.Cell>
</Table.Row>
{/if}
<!-- Parameters -->
{#if modelMeta?.n_params}
<Table.Row>
<Table.Cell class="h-10 align-middle font-medium">Parameters</Table.Cell>
<Table.Cell>{formatParameters(modelMeta.n_params)}</Table.Cell>
</Table.Row>
{/if}
<!-- Embedding Size -->
{#if modelMeta?.n_embd}
<Table.Row>
<Table.Cell class="align-middle font-medium">Embedding Size</Table.Cell>
<Table.Cell>{formatNumber(modelMeta.n_embd)}</Table.Cell>
</Table.Row>
{/if}
<!-- Vocabulary Size -->
{#if modelMeta?.n_vocab}
<Table.Row>
<Table.Cell class="align-middle font-medium">Vocabulary Size</Table.Cell>
<Table.Cell>{formatNumber(modelMeta.n_vocab)} tokens</Table.Cell>
</Table.Row>
{/if}
<!-- Vocabulary Type -->
{#if modelMeta?.vocab_type}
<Table.Row>
<Table.Cell class="align-middle font-medium">Vocabulary Type</Table.Cell>
<Table.Cell class="align-middle capitalize">{modelMeta.vocab_type}</Table.Cell>
</Table.Row>
{/if}
<!-- Total Slots -->
<Table.Row>
<Table.Cell class="align-middle font-medium">Parallel Slots</Table.Cell>
<Table.Cell>{serverProps.total_slots}</Table.Cell>
</Table.Row>
<!-- Modalities -->
{#if modalities.length > 0}
<Table.Row>
<Table.Cell class="align-middle font-medium">Modalities</Table.Cell>
<Table.Cell>
<div class="flex flex-wrap gap-1">
<BadgesModality {modalities} />
</div>
</Table.Cell>
</Table.Row>
{/if}
<!-- Build Info -->
<Table.Row>
<Table.Cell class="align-middle font-medium">Build Info</Table.Cell>
<Table.Cell class="align-middle font-mono text-xs"
>{serverProps.build_info}</Table.Cell
>
</Table.Row>
<!-- Chat Template -->
{#if serverProps.chat_template}
<Table.Row>
<Table.Cell class="align-middle font-medium">Chat Template</Table.Cell>
<Table.Cell class="py-10">
<div class="rounded-md bg-muted p-4">
<pre
class="font-mono text-xs whitespace-pre-wrap">{serverProps.chat_template}</pre>
</div>
</Table.Cell>
</Table.Row>
{/if}
</Table.Body>
</Table.Root>
{/if}
{:else if !isLoadingModels}
<div class="flex items-center justify-center py-8">
<div class="text-sm text-muted-foreground">No model information available</div>
</div>
{/if}
</div>
</Dialog.Content>
</Dialog.Root>