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
co-authored by
Xuan Son Nguyen
Xuan Son Nguyen
parent
49d1701bd2
commit
59778f0196
@@ -0,0 +1,325 @@
|
||||
import { activeProcessingState } from '$lib/stores/chat.svelte';
|
||||
import { config } from '$lib/stores/settings.svelte';
|
||||
import { STATS_UNITS } from '$lib/constants';
|
||||
import type { ApiProcessingState, LiveProcessingStats, LiveGenerationStats } from '$lib/types';
|
||||
|
||||
export interface UseProcessingStateReturn {
|
||||
readonly processingState: ApiProcessingState | null;
|
||||
getProcessingDetails(): string[];
|
||||
getTechnicalDetails(): string[];
|
||||
getProcessingMessage(): string;
|
||||
getPromptProgressText(): string | null;
|
||||
getLiveProcessingStats(): LiveProcessingStats | null;
|
||||
getLiveGenerationStats(): LiveGenerationStats | null;
|
||||
shouldShowDetails(): boolean;
|
||||
startMonitoring(): void;
|
||||
stopMonitoring(): void;
|
||||
}
|
||||
|
||||
/**
|
||||
* useProcessingState - Reactive processing state hook
|
||||
*
|
||||
* This hook provides reactive access to the processing state of the server.
|
||||
* It directly reads from chatStore's reactive state and provides
|
||||
* formatted processing details for UI display.
|
||||
*
|
||||
* **Features:**
|
||||
* - Real-time processing state via direct reactive state binding
|
||||
* - Context and output token tracking
|
||||
* - Tokens per second calculation
|
||||
* - Automatic updates when streaming data arrives
|
||||
* - Supports multiple concurrent conversations
|
||||
*
|
||||
* @returns Hook interface with processing state and control methods
|
||||
*/
|
||||
export function useProcessingState(): UseProcessingStateReturn {
|
||||
let isMonitoring = $state(false);
|
||||
let lastKnownState = $state<ApiProcessingState | null>(null);
|
||||
let lastKnownProcessingStats = $state<LiveProcessingStats | null>(null);
|
||||
|
||||
// Derive processing state reactively from chatStore's direct state
|
||||
const processingState = $derived.by(() => {
|
||||
if (!isMonitoring) {
|
||||
return lastKnownState;
|
||||
}
|
||||
// Read directly from the reactive state export
|
||||
return activeProcessingState();
|
||||
});
|
||||
|
||||
// Track last known state for keepStatsVisible functionality
|
||||
$effect(() => {
|
||||
if (processingState && isMonitoring) {
|
||||
lastKnownState = processingState;
|
||||
}
|
||||
});
|
||||
|
||||
// Track last known processing stats for when promptProgress disappears
|
||||
$effect(() => {
|
||||
if (processingState?.promptProgress) {
|
||||
const { processed, total, time_ms, cache } = processingState.promptProgress;
|
||||
const actualProcessed = processed - cache;
|
||||
const actualTotal = total - cache;
|
||||
|
||||
if (actualProcessed > 0 && time_ms > 0) {
|
||||
const tokensPerSecond = actualProcessed / (time_ms / 1000);
|
||||
lastKnownProcessingStats = {
|
||||
tokensProcessed: actualProcessed,
|
||||
totalTokens: actualTotal,
|
||||
timeMs: time_ms,
|
||||
tokensPerSecond
|
||||
};
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
function getETASecs(done: number, total: number, elapsedMs: number): number | undefined {
|
||||
const elapsedSecs = elapsedMs / 1000;
|
||||
const progressETASecs =
|
||||
done === 0 || elapsedSecs < 0.5
|
||||
? undefined // can be the case for the 0% progress report
|
||||
: elapsedSecs * (total / done - 1);
|
||||
return progressETASecs;
|
||||
}
|
||||
|
||||
function startMonitoring(): void {
|
||||
if (isMonitoring) return;
|
||||
isMonitoring = true;
|
||||
}
|
||||
|
||||
function stopMonitoring(): void {
|
||||
if (!isMonitoring) return;
|
||||
isMonitoring = false;
|
||||
|
||||
// Only clear last known state if keepStatsVisible is disabled
|
||||
const currentConfig = config();
|
||||
if (!currentConfig.keepStatsVisible) {
|
||||
lastKnownState = null;
|
||||
lastKnownProcessingStats = null;
|
||||
}
|
||||
}
|
||||
|
||||
function getProcessingMessage(): string {
|
||||
if (!processingState) {
|
||||
return 'Processing...';
|
||||
}
|
||||
|
||||
switch (processingState.status) {
|
||||
case 'initializing':
|
||||
return 'Initializing...';
|
||||
case 'preparing':
|
||||
if (processingState.progressPercent !== undefined) {
|
||||
return `Processing (${processingState.progressPercent}%)`;
|
||||
}
|
||||
return 'Preparing response...';
|
||||
case 'generating':
|
||||
return '';
|
||||
default:
|
||||
return 'Processing...';
|
||||
}
|
||||
}
|
||||
|
||||
function getProcessingDetails(): string[] {
|
||||
// Use current processing state or fall back to last known state
|
||||
const stateToUse = processingState || lastKnownState;
|
||||
if (!stateToUse) {
|
||||
return [];
|
||||
}
|
||||
|
||||
const details: string[] = [];
|
||||
|
||||
// Show prompt processing progress with ETA during preparation phase
|
||||
if (stateToUse.promptProgress) {
|
||||
const { processed, total, time_ms, cache } = stateToUse.promptProgress;
|
||||
const actualProcessed = processed - cache;
|
||||
const actualTotal = total - cache;
|
||||
|
||||
if (actualProcessed < actualTotal && actualProcessed > 0) {
|
||||
const percent = Math.round((actualProcessed / actualTotal) * 100);
|
||||
const eta = getETASecs(actualProcessed, actualTotal, time_ms);
|
||||
|
||||
if (eta !== undefined) {
|
||||
const etaSecs = Math.ceil(eta);
|
||||
details.push(`Processing ${percent}% (ETA: ${etaSecs}s)`);
|
||||
} else {
|
||||
details.push(`Processing ${percent}%`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Always show context info when we have valid data
|
||||
if (
|
||||
typeof stateToUse.contextTotal === 'number' &&
|
||||
stateToUse.contextUsed >= 0 &&
|
||||
stateToUse.contextTotal > 0
|
||||
) {
|
||||
const contextPercent = Math.round((stateToUse.contextUsed / stateToUse.contextTotal) * 100);
|
||||
|
||||
details.push(
|
||||
`Context: ${stateToUse.contextUsed}/${stateToUse.contextTotal} (${contextPercent}%)`
|
||||
);
|
||||
}
|
||||
|
||||
if (stateToUse.outputTokensUsed > 0) {
|
||||
// Handle infinite max_tokens (-1) case
|
||||
if (stateToUse.outputTokensMax <= 0) {
|
||||
details.push(`Output: ${stateToUse.outputTokensUsed}/∞`);
|
||||
} else {
|
||||
const outputPercent = Math.round(
|
||||
(stateToUse.outputTokensUsed / stateToUse.outputTokensMax) * 100
|
||||
);
|
||||
|
||||
details.push(
|
||||
`Output: ${stateToUse.outputTokensUsed}/${stateToUse.outputTokensMax} (${outputPercent}%)`
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if (stateToUse.tokensPerSecond && stateToUse.tokensPerSecond > 0) {
|
||||
details.push(`${stateToUse.tokensPerSecond.toFixed(1)} ${STATS_UNITS.TOKENS_PER_SECOND}`);
|
||||
}
|
||||
|
||||
if (stateToUse.speculative) {
|
||||
details.push('Speculative decoding enabled');
|
||||
}
|
||||
|
||||
return details;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns technical details without the progress message (for bottom bar)
|
||||
*/
|
||||
function getTechnicalDetails(): string[] {
|
||||
const stateToUse = processingState || lastKnownState;
|
||||
if (!stateToUse) {
|
||||
return [];
|
||||
}
|
||||
|
||||
const details: string[] = [];
|
||||
|
||||
// Always show context info when we have valid data
|
||||
if (
|
||||
typeof stateToUse.contextTotal === 'number' &&
|
||||
stateToUse.contextUsed >= 0 &&
|
||||
stateToUse.contextTotal > 0
|
||||
) {
|
||||
const contextPercent = Math.round((stateToUse.contextUsed / stateToUse.contextTotal) * 100);
|
||||
|
||||
details.push(
|
||||
`Context: ${stateToUse.contextUsed}/${stateToUse.contextTotal} (${contextPercent}%)`
|
||||
);
|
||||
}
|
||||
|
||||
if (stateToUse.outputTokensUsed > 0) {
|
||||
// Handle infinite max_tokens (-1) case
|
||||
if (stateToUse.outputTokensMax <= 0) {
|
||||
details.push(`Output: ${stateToUse.outputTokensUsed}/∞`);
|
||||
} else {
|
||||
const outputPercent = Math.round(
|
||||
(stateToUse.outputTokensUsed / stateToUse.outputTokensMax) * 100
|
||||
);
|
||||
|
||||
details.push(
|
||||
`Output: ${stateToUse.outputTokensUsed}/${stateToUse.outputTokensMax} (${outputPercent}%)`
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if (stateToUse.tokensPerSecond && stateToUse.tokensPerSecond > 0) {
|
||||
details.push(`${stateToUse.tokensPerSecond.toFixed(1)} ${STATS_UNITS.TOKENS_PER_SECOND}`);
|
||||
}
|
||||
|
||||
if (stateToUse.speculative) {
|
||||
details.push('Speculative decoding enabled');
|
||||
}
|
||||
|
||||
return details;
|
||||
}
|
||||
|
||||
function shouldShowDetails(): boolean {
|
||||
return processingState !== null && processingState.status !== 'idle';
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a short progress message with percent
|
||||
*/
|
||||
function getPromptProgressText(): string | null {
|
||||
if (!processingState?.promptProgress) return null;
|
||||
|
||||
const { processed, total, cache } = processingState.promptProgress;
|
||||
|
||||
const actualProcessed = processed - cache;
|
||||
const actualTotal = total - cache;
|
||||
const percent = Math.round((actualProcessed / actualTotal) * 100);
|
||||
const eta = getETASecs(actualProcessed, actualTotal, processingState.promptProgress.time_ms);
|
||||
|
||||
if (eta !== undefined) {
|
||||
const etaSecs = Math.ceil(eta);
|
||||
return `Processing ${percent}% (ETA: ${etaSecs}s)`;
|
||||
}
|
||||
|
||||
return `Processing ${percent}%`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns live processing statistics for display (prompt processing phase)
|
||||
* Returns last known stats when promptProgress becomes unavailable
|
||||
*/
|
||||
function getLiveProcessingStats(): LiveProcessingStats | null {
|
||||
if (processingState?.promptProgress) {
|
||||
const { processed, total, time_ms, cache } = processingState.promptProgress;
|
||||
|
||||
const actualProcessed = processed - cache;
|
||||
const actualTotal = total - cache;
|
||||
|
||||
if (actualProcessed > 0 && time_ms > 0) {
|
||||
const tokensPerSecond = actualProcessed / (time_ms / 1000);
|
||||
|
||||
return {
|
||||
tokensProcessed: actualProcessed,
|
||||
totalTokens: actualTotal,
|
||||
timeMs: time_ms,
|
||||
tokensPerSecond
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
// Return last known stats if promptProgress is no longer available
|
||||
return lastKnownProcessingStats;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns live generation statistics for display (token generation phase)
|
||||
*/
|
||||
function getLiveGenerationStats(): LiveGenerationStats | null {
|
||||
if (!processingState) return null;
|
||||
|
||||
const { tokensDecoded, tokensPerSecond } = processingState;
|
||||
|
||||
if (tokensDecoded <= 0) return null;
|
||||
|
||||
// Calculate time from tokens and speed
|
||||
const timeMs =
|
||||
tokensPerSecond && tokensPerSecond > 0 ? (tokensDecoded / tokensPerSecond) * 1000 : 0;
|
||||
|
||||
return {
|
||||
tokensGenerated: tokensDecoded,
|
||||
timeMs,
|
||||
tokensPerSecond: tokensPerSecond || 0
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
get processingState() {
|
||||
return processingState;
|
||||
},
|
||||
getProcessingDetails,
|
||||
getTechnicalDetails,
|
||||
getProcessingMessage,
|
||||
getPromptProgressText,
|
||||
getLiveProcessingStats,
|
||||
getLiveGenerationStats,
|
||||
shouldShowDetails,
|
||||
startMonitoring,
|
||||
stopMonitoring
|
||||
};
|
||||
}
|
||||
Reference in New Issue
Block a user