model loading, dash
This commit is contained in:
@@ -333,7 +333,8 @@
|
||||
<label for="model-placement-node">Node</label>
|
||||
<select id="model-placement-node"></select>
|
||||
<label id="model-placement-replace" style="display:none"><input type="checkbox" id="model-placement-replace-confirm"> Unload the currently loaded model before loading this one</label>
|
||||
<div class="placement-dialog-actions"><button value="cancel">Cancel</button><button value="confirm">Confirm</button></div>
|
||||
<div id="model-placement-replace-error" class="bad" style="display:none"></div>
|
||||
<div class="placement-dialog-actions"><button value="cancel">Cancel</button><button type="button" id="model-placement-confirm">Confirm</button></div>
|
||||
</form>
|
||||
</dialog>
|
||||
<script>
|
||||
@@ -1828,6 +1829,14 @@ async function releaseAdminModel(model, nodeId) {
|
||||
await refreshActiveTab(true);
|
||||
}
|
||||
|
||||
async function releaseAllNodeModels(nodeId) {
|
||||
if (!confirm("Unload every model from this node?")) return;
|
||||
const result = await apiCall("/v1/nodes/release-all", "POST", { node_id: nodeId });
|
||||
if (!result.ok) return showAdminModelPlacementStatus(result.data.error || "node unload failed", true);
|
||||
showAdminModelPlacementStatus(`Unload queued for ${short(nodeId)}.`);
|
||||
await refreshActiveTab(true);
|
||||
}
|
||||
|
||||
function showAdminModelPlacementStatus(message, isError) {
|
||||
const status = $("admin-model-placement-status");
|
||||
status.textContent = message;
|
||||
@@ -1845,7 +1854,7 @@ function renderAdminNodePool(map) {
|
||||
let html = "";
|
||||
for (const [account, nodes] of Object.entries(groups).sort(([a], [b]) => a.localeCompare(b))) {
|
||||
html += `<div style="margin-top:10px"><b>${esc(short(account, 20))}</b> <span class="dim">${nodes.length} node(s)</span></div>`;
|
||||
html += table(["node", "assignment", "state / slots", "RAM", "GPU / VRAM", "model drive"], nodes.map(node => {
|
||||
html += table(["node", "assignment", "state / slots", "model RAM", "RAM", "GPU / VRAM", "model drive", "action"], nodes.map(node => {
|
||||
const hw = node.hardware_profile || {};
|
||||
const cap = node.capacity || {};
|
||||
// The network map keeps reported resource capacity under `capacity`.
|
||||
@@ -1853,15 +1862,25 @@ function renderAdminNodePool(map) {
|
||||
node.vram_bytes = cap.vram_bytes ?? node.vram_bytes;
|
||||
const disk = hw.model_drive_free_bytes ?? hw.model_path_free_bytes ?? hw.disk_free_bytes;
|
||||
const gpu = hw.gpu_name || (hw.cuda_available ? "CUDA GPU" : "CPU only");
|
||||
return [nodeDisplayCell(node), esc(node.hf_repo || node.model || "unassigned"),
|
||||
const row = [nodeDisplayCell(node), esc(node.hf_repo || node.model || "unassigned"),
|
||||
esc(`${node.stats?.status || "?"} · ${cap.loaded_slots ?? "?"}/${cap.max_loaded_shards ?? node.max_loaded_shards ?? "?"} slots`),
|
||||
esc(gib(cap.loaded_model_bytes)),
|
||||
esc(gib(node.ram_bytes || (hw.ram_mb && hw.ram_mb * 1048576))),
|
||||
esc(`${gpu} · ${gib(node.vram_bytes || (hw.vram_mb && hw.vram_mb * 1048576))}`), esc(gib(disk))];
|
||||
return row.concat([
|
||||
node.shard_start == null ? '<span class="dim">empty</span>' :
|
||||
`<button class="small" data-admin-node-release="${esc(node.node_id)}">unload all</button>`,
|
||||
]);
|
||||
}));
|
||||
}
|
||||
$("admin-node-pool").innerHTML = html || '<div class="empty">no nodes registered</div>';
|
||||
}
|
||||
|
||||
$("admin-node-pool").addEventListener("click", event => {
|
||||
const unload = event.target.closest("[data-admin-node-release]");
|
||||
if (unload) void releaseAllNodeModels(unload.dataset.adminNodeRelease);
|
||||
});
|
||||
|
||||
function renderAdminModelPlacement(models, map) {
|
||||
const nodes = (map && map.nodes) || [];
|
||||
const rows = ((models && models.data) || []).map(model => {
|
||||
@@ -1869,7 +1888,8 @@ function renderAdminModelPlacement(models, map) {
|
||||
const serving = nodes.filter(node => aliases.has(node.model) || aliases.has(node.hf_repo)).length;
|
||||
const downloaded = nodes.filter(node => aliases.has(node.model) || aliases.has(node.hf_repo) ||
|
||||
(node.downloaded_models || []).some(item => aliases.has(item.model) || aliases.has(item.hf_repo))).length;
|
||||
const actions = `<button class="small" data-admin-model-load="${esc(model.id)}">load</button> ` +
|
||||
const loadable = model.id !== "stub-model";
|
||||
const actions = `<button class="small" data-admin-model-load="${esc(model.id)}"${loadable ? "" : " disabled"}>load</button> ` +
|
||||
`<button class="small" data-admin-model-release="${esc(model.id)}"${serving ? "" : " disabled"}>release</button>`;
|
||||
return [esc(model.name || model.id), String(serving), String(downloaded), actions];
|
||||
});
|
||||
@@ -1896,6 +1916,8 @@ function chooseModelPlacementNode(action, model) {
|
||||
select.innerHTML = nodes.map(node => `<option value="${esc(node.node_id)}">${esc(short(node.friendly_name || node.node_id, 20))} — ${esc(node.hf_repo || node.model || "unassigned")}</option>`).join("");
|
||||
const replace = $("model-placement-replace");
|
||||
const replaceConfirm = $("model-placement-replace-confirm");
|
||||
const replaceError = $("model-placement-replace-error");
|
||||
const confirmButton = $("model-placement-confirm");
|
||||
const selectedNode = () => nodes.find(node => node.node_id === select.value);
|
||||
const updateReplacementWarning = () => {
|
||||
const node = selectedNode();
|
||||
@@ -1903,15 +1925,19 @@ function chooseModelPlacementNode(action, model) {
|
||||
modelAliasKey(node.hf_repo || node.model) !== targetAlias;
|
||||
replace.style.display = occupied ? "" : "none";
|
||||
replaceConfirm.checked = false;
|
||||
replaceError.style.display = "none";
|
||||
};
|
||||
select.onchange = updateReplacementWarning;
|
||||
updateReplacementWarning();
|
||||
dialog.onclose = () => {
|
||||
if (dialog.returnValue !== "confirm") return;
|
||||
dialog.onclose = null;
|
||||
confirmButton.onclick = () => {
|
||||
const replacing = replace.style.display !== "none";
|
||||
if (replacing && !replaceConfirm.checked) {
|
||||
return showAdminModelPlacementStatus("Confirm unloading the existing model before replacing it.", true);
|
||||
replaceError.textContent = "Tick the box to confirm that this will unload the current model.";
|
||||
replaceError.style.display = "";
|
||||
return;
|
||||
}
|
||||
dialog.close("confirm");
|
||||
if (action === "load") void requestAdminModelLoad(model, select.value, replacing);
|
||||
else void releaseAdminModel(model, select.value);
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user