Salastil/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-06-16 09:45:24 -04:00
Code Issues Packages Projects Releases Wiki Activity

Show Ollama models in Cookbook Serve

Browse Source
This commit is contained in:
pewdiepie-archdaemon
2026-06-02 07:14:59 +09:00
parent cd53ad01e8
commit ab0a480f30
4 changed files with 65 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
static/js/cookbook.js
+4 -3
View File
@@ -245,6 +245,9 @@ export function _detectToolParser(modelName) {
// ── Backend detection ──
export function _detectBackend(model) {
if (model?.backend === 'ollama' || model?.is_ollama) {
return { backend: 'ollama', label: 'Ollama' };
}
const q = (model.quant || '').toUpperCase();
const sysBackend = String(_hwfitCache?.system?.backend || '').toLowerCase();
const isRocm = sysBackend === 'rocm';
@@ -407,11 +410,9 @@ export function _buildServeCmd(f, modelName, backend) {
cmd += ` || ${_lcpServer}`;
}
} else if (backend === 'ollama') {
const ollamaName = modelName.split('/').pop().toLowerCase().replace(/[-_]gguf$/i, '');
const ollamaPort = f.port || '11434';
const hostEnv = ollamaPort !== '11434' ? `OLLAMA_HOST=0.0.0.0:${ollamaPort} ` : '';
// Start serve in background if not running, then pull model
cmd = `${hostEnv}ollama serve &>/dev/null & sleep 2 && ${hostEnv}ollama pull ${ollamaName} && wait`;
cmd = `${hostEnv}ollama serve`;
} else if (backend === 'diffusers') {
const gpuStr = f.gpus?.trim();
if (gpuStr) cmd += `CUDA_VISIBLE_DEVICES=${gpuStr} `;
static/js/cookbookServe.js
+9 -4
View File
@@ -386,9 +386,9 @@ function _rerenderCachedModels() {
: _isMetal()
// Diffusers (diffusion_server.py) is CUDA-only — omit it on Metal.
? [['llamacpp','llama.cpp'],['ollama','Ollama']]
: [['vllm','vLLM'],['sglang','SGLang'],['llamacpp','llama.cpp'],['diffusers','Diffusers']];
: [['vllm','vLLM'],['sglang','SGLang'],['llamacpp','llama.cpp'],['ollama','Ollama'],['diffusers','Diffusers']];
const backendOpts = _backendChoices.map(([v,l]) => `<option value="${v}"${defaultBackend===v?' selected':''}>${l}</option>`).join('');
panelHtml += `<label>${_l('Backend','Inference engine: vLLM, SGLang, llama.cpp, or Diffusers')}<select class="hwfit-sf" data-field="backend">${backendOpts}</select></label>`;
panelHtml += `<label>${_l('Backend','Inference engine: vLLM, SGLang, llama.cpp, Ollama, or Diffusers')}<select class="hwfit-sf" data-field="backend">${backendOpts}</select></label>`;
panelHtml += `<input type="hidden" class="hwfit-sf" data-field="host" value="${esc(_es.remoteHost || '')}" />`;
panelHtml += `<label>${_l('venv','Path to Python venv or conda env activate script')}<input type="text" class="hwfit-sf hwfit-sf-wide" data-field="venv" value="${esc(sv('venv', _es.envPath || _srvVenv || ''))}" placeholder="~/venv" /></label>`;
panelHtml += `<label>${_l('Port','HTTP port for the API server')}<input type="text" class="hwfit-sf" data-field="port" value="${esc(sv('port', _nextAvailablePort()))}" /></label>`;
@@ -1512,7 +1512,7 @@ export async function _fetchCachedModels() {
const data = await res.json();
_dlWp.destroy();
const ready = data.models.filter(m => m.status === 'ready' && !m.size.includes('MB'));
const ready = data.models.filter(m => m.status === 'ready' && (m.backend === 'ollama' || !m.size.includes('MB')));
const downloading = data.models.filter(m => m.status === 'downloading');
const allModels = [...ready, ...downloading];
_cachedAllModels = allModels;
@@ -1541,7 +1541,8 @@ export async function _fetchCachedModels() {
for (const m of allModels) {
const n = (m.repo_id || '').toLowerCase();
let tag = 'other';
if (m.is_diffusion || /flux|sdxl|stable-diffusion|z-image|qwen-image|diffusion|dreamshar/i.test(n)) tag = 'image';
if (m.backend === 'ollama' || m.is_ollama) tag = 'llm';
else if (m.is_diffusion || /flux|sdxl|stable-diffusion|z-image|qwen-image|diffusion|dreamshar/i.test(n)) tag = 'image';
else if (/whisper|stt|asr/i.test(n)) tag = 'stt';
else if (/tts|cosyvoice|parler/i.test(n)) tag = 'tts';
else if (/embed|bge|minilm|e5-/i.test(n)) tag = 'embedding';
@@ -1553,6 +1554,10 @@ export async function _fetchCachedModels() {
for (const [re, fam] of _families) {
if (re.test(n)) { m._family = fam; _familyMap[fam] = (_familyMap[fam] || 0) + 1; break; }
}
if ((m.backend === 'ollama' || m.is_ollama) && !m._family) {
m._family = 'ollama';
_familyMap.ollama = (_familyMap.ollama || 0) + 1;
}
}
// Render tag chips