Salastil/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-06-16 17:55:26 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improve Cookbook serve diagnostics and recommendations

Browse Source
This commit is contained in:
pewdiepie-archdaemon
2026-06-02 12:15:41 +09:00
parent bdc99d746a
commit 966b53df77
14 changed files with 1113 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files
static/js/cookbook.js
+54 -28
View File
@@ -260,12 +260,31 @@ export function _detectBackend(model) {
const q = (model.quant || '').toUpperCase();
const sysBackend = String(_hwfitCache?.system?.backend || '').toLowerCase();
const isRocm = sysBackend === 'rocm';
const isAppleSilicon = ['metal', 'mps', 'apple'].includes(sysBackend);
const _nm = `${model.repo_id || ''} ${model.path || ''} ${model.name || ''}`.toLowerCase();
if (!isAppleSilicon && (/\bmlx\b|mlx-|_mlx/i.test(_nm) || q.startsWith('MLX'))) {
return { backend: 'unsupported', label: 'Unsupported' };
}
const isAwqLike = /^AWQ|^GPTQ|^NVFP4/.test(q) || q === 'FP8' || /\b(awq|gptq|fp8|nvfp4)\b/i.test(_nm);
const isGgufLike = model.is_gguf || /^Q[2-8]/.test(q) || /^IQ/.test(q) || q === 'GGUF' || _nm.includes('gguf');
// Image gen models → diffusers
if (model.is_image_gen || model.is_diffusion || model._tag === 'image') {
return { backend: 'diffusers', label: 'Diffusers' };
}
// AWQ / GPTQ / FP8 are safetensors GPU-serving formats. Never route them
// through llama.cpp/Ollama just because the host is Mac/Windows; those engines
// need GGUF. The UI will warn/block on Metal where vLLM/SGLang aren't viable.
if (isAwqLike) {
return { backend: 'vllm', label: 'vLLM' };
}
// GGUF → llama.cpp/Ollama-compatible.
if (isGgufLike) {
return { backend: 'llamacpp', label: 'llama.cpp' };
}
// Windows → default to llama.cpp (no vLLM support on Windows)
if (_isWindows()) {
return { backend: 'llamacpp', label: 'llama.cpp' };
@@ -278,19 +297,6 @@ export function _detectBackend(model) {
return { backend: 'llamacpp', label: 'llama.cpp' };
}
// AWQ / GPTQ / FP8 → vLLM
if (/^AWQ|^GPTQ/.test(q) || q === 'FP8') {
return { backend: 'vllm', label: 'vLLM' };
}
// GGUF → llama.cpp. Match the quant tag OR a gguf hint in the repo/path/name:
// a raw .gguf file often has no quant field, which made it fall through to the
// vLLM default below.
const _nm = `${model.repo_id || ''} ${model.path || ''} ${model.name || ''}`.toLowerCase();
if (model.is_gguf || /^Q[2-8]/.test(q) || /^IQ/.test(q) || q === 'GGUF' || _nm.includes('gguf')) {
return { backend: 'llamacpp', label: 'llama.cpp' };
}
// ROCm/AMD machines should not blindly default HF safetensors models to
// vLLM. SGLang is the safer OpenAI-compatible default for plain HF text
// repos there; llama.cpp still wins above whenever the model is GGUF.
@@ -1020,6 +1026,16 @@ function _wireTabEvents(body) {
// Download input
const dlBtn = document.getElementById('cookbook-dl-btn');
const dlInput = document.getElementById('cookbook-dl-repo');
const dlCardToggle = document.getElementById('cookbook-download-card-toggle');
const dlCardBody = document.getElementById('cookbook-download-card-body');
const dlCardArrow = document.getElementById('cookbook-download-card-arrow');
if (dlCardToggle && dlCardBody) {
dlCardToggle.addEventListener('click', () => {
const isOpen = dlCardBody.style.display !== 'none';
dlCardBody.style.display = isOpen ? 'none' : 'block';
if (dlCardArrow) dlCardArrow.style.transform = isOpen ? 'rotate(0deg)' : 'rotate(90deg)';
});
}
if (dlBtn && dlInput) {
function _stripHfUrl(input) {
let repo = input.trim();
@@ -1099,8 +1115,12 @@ function _wireTabEvents(body) {
if (hfToggle && hfList) {
let _loaded = false;
// Per-server VRAM cache so we don't re-probe on every expand
const _vramCache = {};
async function _getSelectedServerVram() {
const _hwCache = {};
function _hfModelLooksAwqLike(m) {
const text = `${m?.repo_id || ''} ${(m?.tags || []).join(' ')}`.toLowerCase();
return /\b(awq|gptq|fp8|4bit|int4)\b/.test(text);
}
async function _getSelectedServerHw() {
// Prefer the "What Fits" dropdown (the main control that shows hardware);
// fall back to the download dropdown. This is the server the list ranks for.
const dlSrv = document.getElementById('hwfit-server-select') || document.getElementById('hwfit-dl-server');
@@ -1117,7 +1137,7 @@ function _wireTabEvents(body) {
}
}
const cacheKey = host || 'local';
if (_vramCache[cacheKey] !== undefined) return _vramCache[cacheKey];
if (_hwCache[cacheKey]) return _hwCache[cacheKey];
// Fetch system info for this server from hwfit
try {
const qp = new URLSearchParams();
@@ -1127,13 +1147,13 @@ function _wireTabEvents(body) {
const r = await fetch(`/api/hwfit/system?${qp}`);
if (r.ok) {
const sys = await r.json();
const v = sys?.gpu_vram_gb || 0;
_vramCache[cacheKey] = v;
return v;
const hw = { vram: sys?.gpu_vram_gb || 0, backend: String(sys?.backend || '').toLowerCase() };
_hwCache[cacheKey] = hw;
return hw;
}
} catch {}
_vramCache[cacheKey] = 0;
return 0;
_hwCache[cacheKey] = { vram: 0, backend: '' };
return _hwCache[cacheKey];
}
async function _loadLatest() {
// Match the Dependencies loader: whirlpool spinner + text label so the
@@ -1152,7 +1172,8 @@ function _wireTabEvents(body) {
} catch {
hfList.innerHTML = '<div class="hwfit-loading">Scanning models…</div>';
}
const vram = await _getSelectedServerVram();
const hwInfo = await _getSelectedServerHw();
const vram = hwInfo.vram || 0;
try {
let lastErr = '';
const _fetchLatest = async (v) => {
@@ -1168,6 +1189,9 @@ function _wireTabEvents(body) {
if (!models.length && vram > 0) {
models = await _fetchLatest(0);
}
if (['rocm', 'metal', 'mps', 'apple', 'generic', 'cpu'].includes(hwInfo.backend)) {
models = models.filter(m => !_hfModelLooksAwqLike(m));
}
if (!models.length) {
// Distinguish "the HF API failed" from "nothing matched" so an outage
// doesn't masquerade as no-fitting-models.
@@ -1351,10 +1375,12 @@ function _renderRecipes() {
// Search group
html += '<div class="cookbook-group" data-backend-group="Search" style="flex:0 0 auto;">';
html += '<div class="admin-card" style="display:flex;flex-direction:column;overflow:hidden;">';
html += '<div style="display:flex;align-items:baseline;gap:8px;margin-bottom:2px;">';
html += '<button type="button" id="cookbook-download-card-toggle" style="display:flex;align-items:baseline;gap:8px;margin-bottom:2px;width:100%;background:transparent;border:0;padding:0;color:inherit;text-align:left;cursor:pointer;">';
html += '<h2 style="margin:0;padding:0;line-height:1;">Download</h2>';
html += '</div>';
html += '<p class="memory-desc doclib-desc" style="margin-top:6px;">Download from <a href="https://huggingface.co/models" target="_blank" rel="noopener" style="color:var(--accent,var(--red));text-decoration:none;"><svg width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="vertical-align:-1px;margin-right:1px;"><path d="M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/><polyline points="15 3 21 3 21 9"/><line x1="10" y1="14" x2="21" y2="3"/></svg>HuggingFace</a> by pasting model link, or download directly in the Scan section below.</p>';
html += '<span id="cookbook-download-card-arrow" style="margin-left:auto;display:inline-block;transition:transform 0.15s;font-size:13px;line-height:1;">\u25B8</span>';
html += '</button>';
html += '<div id="cookbook-download-card-body" style="display:none;">';
html += '<p class="memory-desc doclib-desc" style="margin-top:6px;">Download directly from Scan, or paste a HuggingFace model link.</p>';
html += '<div class="hwfit-container" id="hwfit-container">';
// Section 1: Settings
@@ -1383,7 +1409,7 @@ function _renderRecipes() {
// silently sending downloads to the wrong server. An empty selection means Local; the user
// chooses a remote server explicitly via the dropdown.
// Download input
// Manual download input
html += `<div style="margin-top:7px;margin-bottom:2px;display:flex;gap:4px;align-items:center;">`;
if (_es.servers.length > 1) {
html += `<select class="cookbook-field-input hwfit-dl-server" id="hwfit-dl-server" style="height:28px;position:relative;top:0px;">`;
@@ -1399,7 +1425,7 @@ function _renderRecipes() {
html += `<button class="cookbook-btn cookbook-dl-btn" id="cookbook-dl-btn">Download</button>`;
html += `</div>`;
// Latest HF models that fit — collapsible card list
html += `<div style="margin-top:2px;position:relative;top:-8px;">`;
html += `<div style="margin-top:5px;position:relative;top:-3px;">`;
html += `<div style="display:flex;gap:4px;align-items:center;">`;
html += `<button type="button" class="memory-toolbar-btn" id="cookbook-hf-latest-toggle" style="flex:1;text-align:left;height:26px;display:flex;align-items:center;gap:6px;border-radius:4px;">`;
html += `<span id="cookbook-hf-latest-arrow" style="display:inline-block;transition:transform 0.15s;pointer-events:none;">\u25B8</span>`;
@@ -1411,7 +1437,7 @@ function _renderRecipes() {
html += `</div>`;
// Search section
html += '</div></div></div>';
html += '</div></div></div></div>';
html += '<div class="cookbook-group" data-backend-group="Search">';
html += '<div class="admin-card" style="flex:1;display:flex;flex-direction:column;overflow:hidden;">';
html += '<div style="display:flex;align-items:baseline;gap:8px;margin-bottom:2px;">';