-num_replicas: 1
-gpus_per_replica: 1
-
-# engine_kwargs: # 可选：透传给 vLLM
-# gpu_memory_utilization: 0.4
-""".strip()
- body = f"""
-New Model
-
-
Paste ServingSpec YAML and submit to /api/v2/serve/models.
-
-
-
-
-
-
-
Model
-
-
-
model_key: {html.escape(model_key)}
-
-
-
-
-
-
-
-
-
-
-
Loading...
-
-
Resolved Spec (YAML)
-
(loading)
-
-
Events
-
(loading)
-
-
OpenAI Example
-
(loading)
-
(none)
";
- const rows = events.map(e => {{
- const payload = (e.payload_json || "");
- const short = String(payload).length > 240 ? String(payload).slice(0, 240) + "..." : String(payload);
- return `| ${{e.created_at || ""}} | ${{e.event_type}} | ${{short}} |
`;
- }}).join("");
- return ``;
-}}
-
-async function refresh() {{
- meta.textContent = "Loading...";
- spec.textContent = "(loading)";
- eventsEl.textContent = "(loading)";
- example.textContent = "(loading)";
- try {{
- const obj = await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey));
- const m = obj.model || {{}};
- replicas.value = String(m.num_replicas || 1);
- const endpoint = (m.endpoint && m.endpoint.openai_base_url) || (curOriginWithPort(8000) + "/serve/" + encodeURIComponent(modelKey) + "/v1");
- meta.innerHTML = `
-
-
state: ${{pill(m.state)}}
-
model_id: ${{m.model_id || ""}}
-
source: ${{m.model_source || ""}}
-
endpoint: ${{endpoint}}
- `;
- spec.textContent = obj.resolved_spec_yaml || "";
- eventsEl.innerHTML = renderEvents(obj.events || []);
- const base = endpoint;
- const mid = m.model_id || "";
- example.textContent = `curl -sS -H 'Content-Type: application/json' \\\\\\n -X POST ${{base}}/chat/completions \\\\\\n --data-binary '{{\\"model\\":\\"${{mid}}\\",\\"messages\\":[{{\\"role\\":\\"user\\",\\"content\\":\\"hello\\"}}],\\"max_tokens\\":16,\\"stream\\":false}}' | python3 -m json.tool`;
- }} catch (e) {{
- meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
- spec.textContent = "";
- eventsEl.textContent = "";
- example.textContent = "";
- }}
-}}
-
-document.getElementById("scale").onclick = async () => {{
- const n = Number(replicas.value || "1");
- if (!Number.isFinite(n) || n < 1) return;
- try {{
- await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey), {{ method: "PATCH", headers: {{ "Content-Type": "application/json" }}, body: JSON.stringify({{ num_replicas: n }}) }});
- await refresh();
- }} catch (e) {{
- meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
- }}
-}};
-
-document.getElementById("delete").onclick = async () => {{
- if (!confirm("Delete this model?")) return;
- try {{
- await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey), {{ method: "DELETE" }});
- await refresh();
- }} catch (e) {{
- meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
- }}
-}};
-
-refresh();
-""".strip()
- return HTMLResponse(content=_page("Model", "serving", body, script))
-
- @app.get("/ui/data")
- async def ui_data() -> HTMLResponse:
- body = """
-Data
-
-
User files live under your home directory. Keep long-term artifacts in models/ or datasets/.
-
-
-
-
-
Username
-
-
-
-
-
-
-
-
SFTPGo password
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- You can also use an SFTP client (e.g. FileZilla) with the same username/password.
- Host:
-
-
-
-
Admin
-
-
- This page requires the
admin token (set it in
Login).
-
-
-
-
Create user
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Loading...
-
- ${esc(uid)} |
- ${esc(created)} |
- ${esc(updated)} |
-
-
- ${esc(tokShort)}
-
-
-
- token_created_at: ${esc(tCreated)}; last_used_at: ${esc(tUsed)}
- |
-
`;
- }
- out.innerHTML = `
-
- | User | Created | Updated | Token |
|---|
- ${users.map(row).join("") || "| (none) |
"}
-
- `;
- for (const btn of out.querySelectorAll("button[data-copy]")) {
- btn.onclick = async () => { await copyText(btn.getAttribute("data-copy") || ""); };
- }
- for (const btn of out.querySelectorAll("button[data-issue]")) {
- btn.onclick = async () => {
- const uid = btn.getAttribute("data-issue");
- if (!uid) return;
- try {
- const r = await apiJson("/api/v2/users/" + encodeURIComponent(uid) + "/tokens", { method: "POST" });
- createMsg.textContent = "Issued token:\\n" + fmtJson(r);
- await refresh();
- } catch (e) {
- createMsg.textContent = "Error issuing token: " + (e.status || "") + "\\n" + (e.body || String(e));
- }
- };
- }
- } catch (e) {
- out.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
- }
-}
-
-document.getElementById("refresh").onclick = refresh;
-document.getElementById("create-user").onclick = async () => {
- createMsg.textContent = "Creating...";
- const user_id = (userIdEl.value || "").trim();
- const display_name = (displayNameEl.value || "").trim();
- if (!user_id) { createMsg.textContent = "user_id is required"; return; }
- const payload = { user_id: user_id };
- if (display_name) payload.display_name = display_name;
- try {
- const r = await apiJson("/api/v2/users", { method: "POST", headers: {"Content-Type":"application/json"}, body: JSON.stringify(payload) });
- createMsg.textContent = "Created:\\n" + fmtJson(r);
- userIdEl.value = "";
- displayNameEl.value = "";
- await refresh();
- } catch (e) {
- createMsg.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
- }
-};
-
-refresh();
-""".strip()
- return HTMLResponse(content=_page("Admin", "admin", body, script))
diff --git a/src/mvp/py/argus/ui/__init__.py b/src/mvp/py/argus/ui/__init__.py
new file mode 100644
index 0000000..4ebedf8
--- /dev/null
+++ b/src/mvp/py/argus/ui/__init__.py
@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+from .routes import register_ui_routes
+
+__all__ = ["register_ui_routes"]
+
diff --git a/src/mvp/py/argus/ui/assets/__init__.py b/src/mvp/py/argus/ui/assets/__init__.py
new file mode 100644
index 0000000..3ce55a6
--- /dev/null
+++ b/src/mvp/py/argus/ui/assets/__init__.py
@@ -0,0 +1,2 @@
+from __future__ import annotations
+
diff --git a/src/mvp/py/argus/ui/assets/base_css.py b/src/mvp/py/argus/ui/assets/base_css.py
new file mode 100644
index 0000000..0287424
--- /dev/null
+++ b/src/mvp/py/argus/ui/assets/base_css.py
@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+BASE_CSS = """
+:root { --bg:#0b1020; --panel:#111a33; --muted:#95a3c6; --fg:#e8eeff; --accent:#7aa2ff; --danger:#ff6b6b; --ok:#3ddc97; }
+* { box-sizing: border-box; }
+body { margin:0; font-family: ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto, Helvetica, Arial; background:var(--bg); color:var(--fg); }
+a { color:var(--accent); text-decoration:none; }
+.layout { display:flex; min-height:100vh; }
+.nav { width: 240px; padding:16px; background: linear-gradient(180deg, #0e1630, #0b1020); border-right: 1px solid rgba(255,255,255,0.06); }
+.brand { font-weight: 700; letter-spacing: .2px; margin-bottom: 12px; }
+.nav a { display:block; padding:10px 10px; border-radius:10px; color: var(--fg); opacity: .9; }
+.nav a.active { background: rgba(122,162,255,0.14); border: 1px solid rgba(122,162,255,0.22); }
+.nav a:hover { background: rgba(255,255,255,0.06); }
+.main { flex:1; padding: 20px 24px; }
+.card { background: rgba(255,255,255,0.04); border: 1px solid rgba(255,255,255,0.08); border-radius: 14px; padding: 16px; }
+.row { display:flex; gap: 12px; align-items:center; flex-wrap: wrap; }
+.muted { color: var(--muted); }
+.btn { border: 1px solid rgba(255,255,255,0.16); background: rgba(255,255,255,0.06); color: var(--fg); padding: 10px 12px; border-radius: 10px; cursor: pointer; }
+.btn:hover { background: rgba(255,255,255,0.10); }
+.btn.active { background: rgba(122,162,255,0.14); border-color: rgba(122,162,255,0.22); }
+.btn.danger { border-color: rgba(255,107,107,0.35); background: rgba(255,107,107,0.10); }
+.pill { display:inline-block; padding: 2px 10px; border-radius: 999px; border: 1px solid rgba(255,255,255,0.16); font-size: 12px; }
+.pill.ok { border-color: rgba(61,220,151,0.35); background: rgba(61,220,151,0.12); }
+.pill.bad { border-color: rgba(255,107,107,0.35); background: rgba(255,107,107,0.12); }
+textarea, input { width: 100%; color: var(--fg); background: rgba(255,255,255,0.06); border: 1px solid rgba(255,255,255,0.12); border-radius: 12px; padding: 10px 12px; outline: none; }
+select { color: var(--fg); background: rgba(255,255,255,0.06); border: 1px solid rgba(255,255,255,0.12); border-radius: 12px; padding: 10px 12px; outline: none; }
+select option { color: var(--fg); background: #0e1630; }
+button:disabled { opacity: .45; cursor: not-allowed; }
+pre { white-space: pre-wrap; word-break: break-word; }
+table { width:100%; border-collapse: collapse; }
+th, td { padding: 10px 8px; border-bottom: 1px solid rgba(255,255,255,0.08); text-align:left; }
+""".strip()
+
diff --git a/src/mvp/py/argus/ui/assets/base_js.py b/src/mvp/py/argus/ui/assets/base_js.py
new file mode 100644
index 0000000..ea73324
--- /dev/null
+++ b/src/mvp/py/argus/ui/assets/base_js.py
@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+BASE_JS = """
+function mvpTokenGet() {
+ return (localStorage.getItem("mvp_token") || "").trim();
+}
+function mvpTokenSet(v) {
+ localStorage.setItem("mvp_token", (v || "").trim());
+}
+function mvpSftpPasswordGet() {
+ return (localStorage.getItem("mvp_sftp_password") || "").trim();
+}
+function mvpSftpPasswordSet(v) {
+ localStorage.setItem("mvp_sftp_password", (v || "").trim());
+}
+async function apiFetch(path, opts) {
+ opts = opts || {};
+ opts.headers = opts.headers || {};
+ const tok = mvpTokenGet();
+ if (tok) opts.headers["Authorization"] = "Bearer " + tok;
+ return fetch(path, opts);
+}
+async function apiJson(path, opts) {
+ const resp = await apiFetch(path, opts);
+ const text = await resp.text();
+ if (!resp.ok) {
+ const err = new Error("HTTP " + resp.status);
+ err.status = resp.status;
+ err.body = text;
+ throw err;
+ }
+ return JSON.parse(text);
+}
+function fmtJson(obj) {
+ try { return JSON.stringify(obj, null, 2); } catch (e) { return String(obj); }
+}
+function curOriginWithPort(port) {
+ const proto = window.location.protocol;
+ const host = window.location.hostname;
+ return proto + "//" + host + ":" + port;
+}
+async function copyText(v) {
+ if (!v) return false;
+ try {
+ await navigator.clipboard.writeText(v);
+ return true;
+ } catch (e) {
+ // Fallback for non-secure contexts (http) or older browsers.
+ try {
+ const ta = document.createElement("textarea");
+ ta.value = v;
+ ta.style.position = "fixed";
+ ta.style.opacity = "0";
+ document.body.appendChild(ta);
+ ta.focus();
+ ta.select();
+ const ok = document.execCommand("copy");
+ document.body.removeChild(ta);
+ return ok;
+ } catch (e2) {
+ return false;
+ }
+ }
+}
+document.addEventListener("DOMContentLoaded", () => {
+ const el = document.getElementById("nav-ray-dashboard");
+ if (el) el.href = curOriginWithPort(8265);
+});
+""".strip()
+
diff --git a/src/mvp/py/argus/ui/layout/__init__.py b/src/mvp/py/argus/ui/layout/__init__.py
new file mode 100644
index 0000000..3ce55a6
--- /dev/null
+++ b/src/mvp/py/argus/ui/layout/__init__.py
@@ -0,0 +1,2 @@
+from __future__ import annotations
+
diff --git a/src/mvp/py/argus/ui/layout/nav.py b/src/mvp/py/argus/ui/layout/nav.py
new file mode 100644
index 0000000..d783a7e
--- /dev/null
+++ b/src/mvp/py/argus/ui/layout/nav.py
@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+import html
+
+
+def nav(active: str) -> str:
+ links = [
+ ("login", "/ui/login", "Login"),
+ ("tasks", "/ui/tasks", "Tasks"),
+ ("serving", "/ui/serving", "Serving"),
+ ("new", "/ui/tasks/new", "New Task"),
+ ("data", "/ui/data", "Data"),
+ ("admin", "/ui/admin", "Admin"),
+ ("ray", "#", "Ray Dashboard"),
+ ]
+ items: list[str] = []
+ for key, href, label in links:
+ cls = "active" if key == active else ""
+ extra = ""
+ if key == "ray":
+ extra = ' id="nav-ray-dashboard" target="_blank" rel="noopener"'
+ items.append(f'{html.escape(label)}')
+ return "\n".join(items)
+
diff --git a/src/mvp/py/argus/ui/layout/page.py b/src/mvp/py/argus/ui/layout/page.py
new file mode 100644
index 0000000..b5f0264
--- /dev/null
+++ b/src/mvp/py/argus/ui/layout/page.py
@@ -0,0 +1,36 @@
+from __future__ import annotations
+
+import html
+
+from ..assets.base_css import BASE_CSS
+from ..assets.base_js import BASE_JS
+from .nav import nav
+
+
+def page(title: str, active: str, body: str, script: str = "") -> str:
+ return f"""
+
+
+
+
+ {html.escape(title)}
+
+
+
+
+
+
+ {body}
+
+
Admin
+
+
+ This page requires the
admin token (set it in
Login).
+
+
+
+
Create user
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Loading...
+
+ ${esc(uid)} |
+ ${esc(created)} |
+ ${esc(updated)} |
+
+
+ ${esc(tokShort)}
+
+
+
+ token_created_at: ${esc(tCreated)}; last_used_at: ${esc(tUsed)}
+ |
+
`;
+ }
+ out.innerHTML = `
+
+ | User | Created | Updated | Token |
|---|
+ ${users.map(row).join("") || "| (none) |
"}
+
+ `;
+ for (const btn of out.querySelectorAll("button[data-copy]")) {
+ btn.onclick = async () => { await copyText(btn.getAttribute("data-copy") || ""); };
+ }
+ for (const btn of out.querySelectorAll("button[data-issue]")) {
+ btn.onclick = async () => {
+ const uid = btn.getAttribute("data-issue");
+ if (!uid) return;
+ try {
+ const r = await apiJson("/api/v2/users/" + encodeURIComponent(uid) + "/tokens", { method: "POST" });
+ createMsg.textContent = "Issued token:\\n" + fmtJson(r);
+ await refresh();
+ } catch (e) {
+ createMsg.textContent = "Error issuing token: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }
+ };
+ }
+ } catch (e) {
+ out.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }
+}
+
+document.getElementById("refresh").onclick = refresh;
+document.getElementById("create-user").onclick = async () => {
+ createMsg.textContent = "Creating...";
+ const user_id = (userIdEl.value || "").trim();
+ const display_name = (displayNameEl.value || "").trim();
+ if (!user_id) { createMsg.textContent = "user_id is required"; return; }
+ const payload = { user_id: user_id };
+ if (display_name) payload.display_name = display_name;
+ try {
+ const r = await apiJson("/api/v2/users", { method: "POST", headers: {"Content-Type":"application/json"}, body: JSON.stringify(payload) });
+ createMsg.textContent = "Created:\\n" + fmtJson(r);
+ userIdEl.value = "";
+ displayNameEl.value = "";
+ await refresh();
+ } catch (e) {
+ createMsg.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }
+};
+
+refresh();
+""".strip()
+ return HTMLResponse(content=page("Admin", "admin", body, script))
+
diff --git a/src/mvp/py/argus/ui/pages/data.py b/src/mvp/py/argus/ui/pages/data.py
new file mode 100644
index 0000000..120dbde
--- /dev/null
+++ b/src/mvp/py/argus/ui/pages/data.py
@@ -0,0 +1,93 @@
+from __future__ import annotations
+
+from fastapi import FastAPI
+from fastapi.responses import HTMLResponse
+
+from ..layout.page import page
+
+
+def register(app: FastAPI) -> None:
+ @app.get("/ui/data")
+ async def ui_data() -> HTMLResponse:
+ body = """
+Data
+
+
User files live under your home directory. Keep long-term artifacts in models/ or datasets/.
+
+
+
+
+
Username
+
+
+
+
+
+
+
+
SFTPGo password
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ You can also use an SFTP client (e.g. FileZilla) with the same username/password.
+ Host:
+
+
+
+
Login
+
+
Paste your API token (without the Bearer prefix).
+
+
+
+
+
+
+
+
User Info
+
Shown after login via /api/v2/me.
+
+
+
+
+
+
(not loaded)
+
+
W&B
+
Weights & Biases local server (v3.6). Metrics are written by training jobs; this UI is for viewing.
+
+
+
+
project: (unknown)
+
base_url (job runtime): (unknown)
+
Serving
+
+""".strip()
+ script = """
+document.getElementById("nav-ray-dashboard").href = curOriginWithPort(8265);
+const out = document.getElementById("out");
+
+function pill(state) {
+ const s = String(state || "");
+ if (s === "RUNNING") return `${s}`;
+ if (s === "FAILED") return `${s}`;
+ return `${s}`;
+}
+
+async function refresh() {
+ out.textContent = "Loading...";
+ try {
+ const lim = 50;
+ const off = Number(localStorage.getItem("mvp_serving_offset") || "0") || 0;
+ const resp = await apiJson("/api/v2/serve/models?limit=" + lim + "&offset=" + off + "&include_deleted=0");
+ const items = resp.items || [];
+ const hasMore = !!resp.has_more;
+ const pageNo = Math.floor(off / lim) + 1;
+ const prevDisabled = off <= 0;
+ const nextDisabled = !hasMore;
+
+ const baseHint = curOriginWithPort(8000) + "/serve//v1";
+ function row(m) {
+ const endpoint = (m.endpoint && m.endpoint.openai_base_url) || (curOriginWithPort(8000) + "/serve/" + encodeURIComponent(m.model_key) + "/v1");
+ return `
+ | ${m.model_key} |
+ ${m.model_id} |
+ ${pill(m.state)} |
+ ${m.num_replicas} × ${m.gpus_per_replica} GPU |
+ ${endpoint} |
+ ${m.updated_at || ""} |
+
`;
+ }
+ const rows = items.map(row).join("");
+
+ out.innerHTML = `
+
+
Per-model OpenAI base: ${baseHint}
+
+ Page ${pageNo}
+
+
+
+
+ | Model Key | Model ID | State | Resources | Endpoint | Updated |
|---|
+ ${rows || "| (none) |
"}
+
+ `;
+
+ const prevBtn = document.getElementById("prev");
+ const nextBtn = document.getElementById("next");
+ if (prevBtn) prevBtn.onclick = () => { localStorage.setItem("mvp_serving_offset", String(Math.max(0, off - lim))); refresh(); };
+ if (nextBtn) nextBtn.onclick = () => { localStorage.setItem("mvp_serving_offset", String(off + lim)); refresh(); };
+ } catch (e) {
+ let text = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ if (e.body && String(e.body).includes("serving is not enabled")) {
+ text = "Serving is not enabled in server config.\\nAsk admin to enable `serving:` in dev.yaml.";
+ }
+ out.textContent = text;
+ }
+}
+
+document.getElementById("refresh").onclick = refresh;
+refresh();
+""".strip()
+ return HTMLResponse(content=page("Serving", "serving", body, script))
+
+ @app.get("/ui/serving/new")
+ async def ui_serving_new() -> HTMLResponse:
+ example = """# ServingSpec (YAML)
+# 说明：
+# - model_id: 这里是 suffix（平台会自动加前缀：--）
+# - model_source: 本地模型路径（支持 $HOME 宏；推荐使用 $HOME/common/hf 指向共享 HF cache）
+#
+# 常用路径：
+# - $HOME/common/hf -> /private/hf
+# - $HOME -> /private/users/
+#
+model_id: qwen-0.5b
+model_source: $HOME/common/hf/hub/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/
+num_replicas: 1
+gpus_per_replica: 1
+
+# engine_kwargs: # 可选：透传给 vLLM
+# gpu_memory_utilization: 0.4
+""".strip()
+ body = f"""
+New Model
+
+
Paste ServingSpec YAML and submit to /api/v2/serve/models.
+
+
+
+
+
+
+
Model
+
+
+
model_key: {html.escape(model_key)}
+
+
+
+
+
+
+
+
+
+
+
Loading...
+
+
Resolved Spec (YAML)
+
(loading)
+
+
Events
+
(loading)
+
+
OpenAI Example
+
(loading)
+
(none)
";
+ const rows = events.map(e => {{
+ const payload = (e.payload_json || "");
+ const short = String(payload).length > 240 ? String(payload).slice(0, 240) + "..." : String(payload);
+ return `| ${{e.created_at || ""}} | ${{e.event_type}} | ${{short}} |
`;
+ }}).join("");
+ return ``;
+}}
+
+async function refresh() {{
+ meta.textContent = "Loading...";
+ spec.textContent = "(loading)";
+ eventsEl.textContent = "(loading)";
+ example.textContent = "(loading)";
+ try {{
+ const obj = await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey));
+ const m = obj.model || {{}};
+ replicas.value = String(m.num_replicas || 1);
+ const endpoint = (m.endpoint && m.endpoint.openai_base_url) || (curOriginWithPort(8000) + "/serve/" + encodeURIComponent(modelKey) + "/v1");
+ meta.innerHTML = `
+
+
state: ${{pill(m.state)}}
+
model_id: ${{m.model_id || ""}}
+
source: ${{m.model_source || ""}}
+
endpoint: ${{endpoint}}
+ `;
+ spec.textContent = obj.resolved_spec_yaml || "";
+ eventsEl.innerHTML = renderEvents(obj.events || []);
+ const base = endpoint;
+ const mid = m.model_id || "";
+ example.textContent = `curl -sS -H 'Content-Type: application/json' \\\\\\n -X POST ${{base}}/chat/completions \\\\\\n --data-binary '{{\\"model\\":\\"${{mid}}\\",\\"messages\\":[{{\\"role\\":\\"user\\",\\"content\\":\\"hello\\"}}],\\"max_tokens\\":16,\\"stream\\":false}}' | python3 -m json.tool`;
+ }} catch (e) {{
+ meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ spec.textContent = "";
+ eventsEl.textContent = "";
+ example.textContent = "";
+ }}
+}}
+
+document.getElementById("scale").onclick = async () => {{
+ const n = Number(replicas.value || "1");
+ if (!Number.isFinite(n) || n < 1) return;
+ try {{
+ await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey), {{ method: "PATCH", headers: {{ "Content-Type": "application/json" }}, body: JSON.stringify({{ num_replicas: n }}) }});
+ await refresh();
+ }} catch (e) {{
+ meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }}
+}};
+
+document.getElementById("delete").onclick = async () => {{
+ if (!confirm("Delete this model?")) return;
+ try {{
+ await apiJson("/api/v2/serve/models/" + encodeURIComponent(modelKey), {{ method: "DELETE" }});
+ await refresh();
+ }} catch (e) {{
+ meta.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }}
+}};
+
+refresh();
+""".strip()
+ return HTMLResponse(content=page("Model", "serving", body, script))
+
diff --git a/src/mvp/py/argus/ui/pages/task_detail.py b/src/mvp/py/argus/ui/pages/task_detail.py
new file mode 100644
index 0000000..e70fdd6
--- /dev/null
+++ b/src/mvp/py/argus/ui/pages/task_detail.py
@@ -0,0 +1,88 @@
+from __future__ import annotations
+
+import html
+
+from fastapi import FastAPI
+from fastapi.responses import HTMLResponse
+
+from ..layout.page import page
+
+
+def register(app: FastAPI) -> None:
+ @app.get("/ui/tasks/{task_id}")
+ async def ui_task_detail(task_id: str) -> HTMLResponse:
+ safe_id = html.escape(task_id)
+ body = f"""
+Task: {safe_id}
+
+
+
+
W&B
+
This is a best-effort hint. Run name maps to ray_submission_id (attempt).
+
+
+
+
project: (unknown)
+
run: (unknown)
+
+
TaskSpec (YAML)
+
Resolved TaskSpec (includes default values; submission_id reflects latest attempt when available).
+
+
Loading...
+
Logs: {safe_id}
+
+
+
+
+
Back
+
+
+
Loading...
+
New Task
+
+
+ Paste TaskSpec YAML and submit to API server.
+ Basic tasks require code_path; Advanced tasks use kind: advanced with a custom command.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Tasks
+
+""".strip()
+ script = """
+const out = document.getElementById("out");
+async function refresh() {
+ out.textContent = "Loading...";
+ try {
+ const q = await apiJson("/api/v2/queue");
+ const completedLimit = 25;
+ const completedOffset = Number(localStorage.getItem("mvp_completed_offset") || "0") || 0;
+ const done = await apiJson("/api/v2/tasks?limit=" + completedLimit + "&offset=" + completedOffset + "&states=SUCCEEDED,FAILED,CANCELED");
+
+ function pill(state) {
+ const s = String(state || "");
+ if (s === "SUCCEEDED") return `${s}`;
+ if (s === "FAILED") return `${s}`;
+ if (s === "CANCELED") return `${s}`;
+ if (s === "RUNNING") return `${s}`;
+ if (s === "QUEUED" || s === "PENDING_RESOURCES" || s === "SUBMITTING" || s === "SUBMITTED") return `${s}`;
+ return `${s}`;
+ }
+ function row(t) {
+ const id = t.task_id;
+ return `
+ | ${id} |
+ ${t.workload} |
+ ${pill(t.state)} |
+ ${t.nnodes} x ${t.n_gpus_per_node} GPU |
+ ${t.updated_at || ""} |
+
`;
+ }
+
+ const running = (q.running || []).map(row).join("");
+ const pending = (q.pending || []).map(row).join("");
+ const doneRows = (done.tasks || []).map(row).join("");
+ const pageNo = Math.floor(completedOffset / completedLimit) + 1;
+ const prevDisabled = completedOffset <= 0;
+ const nextDisabled = !done.has_more;
+ out.innerHTML = `
+ Tip: configure token in
Login.
Running
+ | Task | Workload | State | Resources | Updated |
|---|
${running || "| (none) |
"}
+
+ Pending
+ | Task | Workload | State | Resources | Updated |
|---|
${pending || "| (none) |
"}
+
+ Completed
+
+
Page ${pageNo}
+
+
+
+
+
| Task | Workload | State | Resources | Updated |
|---|
${doneRows || "| (none) |
"}
+ `;
+
+ const prevBtn = document.getElementById("done-prev");
+ const nextBtn = document.getElementById("done-next");
+ if (prevBtn) prevBtn.onclick = () => {
+ const cur = Number(localStorage.getItem("mvp_completed_offset") || "0") || 0;
+ const next = Math.max(0, cur - completedLimit);
+ localStorage.setItem("mvp_completed_offset", String(next));
+ refresh();
+ };
+ if (nextBtn) nextBtn.onclick = () => {
+ const cur = Number(localStorage.getItem("mvp_completed_offset") || "0") || 0;
+ const next = cur + completedLimit;
+ localStorage.setItem("mvp_completed_offset", String(next));
+ refresh();
+ };
+ } catch (e) {
+ out.textContent = "Error: " + (e.status || "") + "\\n" + (e.body || String(e));
+ }
+}
+document.getElementById("refresh").onclick = refresh;
+refresh();
+""".strip()
+ return HTMLResponse(content=page("Tasks", "tasks", body, script))
+
diff --git a/src/mvp/py/argus/ui/routes.py b/src/mvp/py/argus/ui/routes.py
new file mode 100644
index 0000000..142ac67
--- /dev/null
+++ b/src/mvp/py/argus/ui/routes.py
@@ -0,0 +1,22 @@
+from __future__ import annotations
+
+from fastapi import FastAPI
+from fastapi.responses import RedirectResponse
+
+from .pages import admin, data, login, serving, task_detail, task_logs, task_new, tasks
+
+
+def register_ui_routes(app: FastAPI) -> None:
+ @app.get("/ui")
+ async def ui_root() -> RedirectResponse:
+ return RedirectResponse(url="/ui/tasks")
+
+ login.register(app)
+ tasks.register(app)
+ task_new.register(app)
+ task_detail.register(app)
+ task_logs.register(app)
+ serving.register(app)
+ data.register(app)
+ admin.register(app)
+
diff --git a/src/mvp/scripts/30_prepare_data_and_model.sh b/src/mvp/scripts/30_prepare_data_and_model.sh
index 4c4a79f..53dac92 100755
--- a/src/mvp/scripts/30_prepare_data_and_model.sh
+++ b/src/mvp/scripts/30_prepare_data_and_model.sh
@@ -36,7 +36,7 @@ dexec "${HEAD_CONTAINER}" bash -lc "
"
echo "[head] prepare PPO dataset (gsm8k RL parquet) -> ${PPO_DATA_DIR}"
-dexec "${HEAD_CONTAINER}" bash -lc "if [[ -f '${PPO_DATA_DIR}/train.parquet' && -f '${PPO_DATA_DIR}/test.parquet' ]]; then echo 'ppo_dataset_exists: skip'; else python3 /workspace/verl/examples/data_preprocess/gsm8k.py --local_save_dir '${PPO_DATA_DIR}'; fi"
+dexec "${HEAD_CONTAINER}" bash -lc "if [[ -f '${PPO_DATA_DIR}/train.parquet' && -f '${PPO_DATA_DIR}/test.parquet' ]]; then echo 'ppo_dataset_exists: skip'; else PYTHONPATH=\"/workspace/verl:${PYTHONPATH:-}\" python3 /workspace/verl/examples/data_preprocess/gsm8k.py --local_save_dir '${PPO_DATA_DIR}'; fi"
echo "[head] prepare SFT dataset (gsm8k messages parquet) -> ${SFT_DATA_DIR}"
if dexec "${HEAD_CONTAINER}" bash -lc "test -f '${SFT_DATA_DIR}/train.parquet'"; then
@@ -82,6 +82,7 @@ PY_CODE="$(cat <<'PY'
import os
model_id = os.environ["MODEL_ID"]
+link_name = model_id.replace("/", "--")
hf_home = os.environ.get("HF_HOME", "/private/hf")
os.environ.setdefault("HF_HOME", hf_home)
@@ -91,12 +92,27 @@ os.environ.setdefault("TRANSFORMERS_CACHE", os.path.join(hf_home, "transformers"
from huggingface_hub import snapshot_download
try:
- snapshot_download(repo_id=model_id, local_files_only=True)
- print("model_cache_exists: skip", model_id)
+ path = snapshot_download(repo_id=model_id, local_files_only=True)
+ print("model_cache_exists: skip", model_id, path)
except Exception:
print("model_cache_missing: downloading", model_id)
- snapshot_download(repo_id=model_id)
- print("model_cached_ok:", model_id)
+ path = snapshot_download(repo_id=model_id)
+ print("model_cached_ok:", model_id, path)
+
+# v3.0 path policy: use a stable symlink under /private/common/models/...
+common_models_dir = "/private/common/models"
+os.makedirs(common_models_dir, exist_ok=True)
+dst = os.path.join(common_models_dir, link_name)
+try:
+ if os.path.islink(dst) or os.path.exists(dst):
+ os.unlink(dst)
+except Exception:
+ pass
+try:
+ os.symlink(path, dst)
+ print("model_common_link_ok:", dst)
+except Exception as e:
+ print("WARN: model_common_link_failed:", dst, repr(e))
PY
)"
diff --git a/src/mvp/scripts/run_all_v30_api.sh b/src/mvp/scripts/run_all_v30_api.sh
index f2e9917..4be775c 100755
--- a/src/mvp/scripts/run_all_v30_api.sh
+++ b/src/mvp/scripts/run_all_v30_api.sh
@@ -20,7 +20,7 @@ RESET_SFTPGO="${RESET_SFTPGO:-0}"
EXPECTED_RAY_NODES="${EXPECTED_RAY_NODES:-3}" # head + 2 workers
CLUSTER_NAME="${CLUSTER_NAME:-argus-ray}"
-CONFIG_IN_CONTAINER="${CONFIG_IN_CONTAINER:-/workspace/mvp/configs/dev_v30.yaml}"
+CONFIG_IN_CONTAINER="${CONFIG_IN_CONTAINER:-/workspace/mvp/configs/dev.yaml}"
SFTPGO_ADMIN_PASSWORD="${SFTPGO_ADMIN_PASSWORD:-my-dev-sftpgo-admin}"
export SFTPGO_ADMIN_PASSWORD
@@ -105,7 +105,12 @@ submit_taskspec_inline() {
local resp
resp="$(curl -sS -H "Authorization: Bearer ${token}" -H "Content-Type: application/yaml" --data-binary "${yaml_body}" "${API_ADDR}/api/v2/tasks")"
echo "[host] submit_resp: ${resp}" >&2
- printf '%s' "${resp}" | python3 -c 'import sys,json; print(json.load(sys.stdin)["task_id"])'
+ printf '%s' "${resp}" | python3 -c 'import sys,json; o=json.load(sys.stdin); tid=o.get("task_id",""); print(tid) if tid else sys.exit(42)'
+ local rc=$?
+ if [[ "${rc}" != "0" ]]; then
+ echo "ERROR: submit failed: ${resp}" >&2
+ return 1
+ fi
}
wait_task() {
@@ -154,12 +159,15 @@ ray_wait_ready 60
echo "[host] wait sftpgo ready"
sftpgo_wait_ready 60 "http://127.0.0.1:8081/api/v2/token"
-echo "[host] render v3.0 config with SFTPGo container IP (work around docker DNS issues)"
+echo "[host] render config with SFTPGo container IP (work around docker DNS issues)"
SFTPGO_IP="$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' argus-sftpgo)"
-RENDERED_CFG_HOST_PATH="/tmp/dev_v30_rendered.yaml"
-sed -E "s#^(\\s*admin_api_base:) .*#\\1 \"http://${SFTPGO_IP}:8080/api/v2\"#g" "${ROOT_DIR}/configs/dev_v30.yaml" >"${RENDERED_CFG_HOST_PATH}"
-docker cp "${RENDERED_CFG_HOST_PATH}" "${HEAD_CONTAINER}:/tmp/dev_v30_rendered.yaml"
-CONFIG_IN_CONTAINER="/tmp/dev_v30_rendered.yaml"
+RENDERED_CFG_HOST_PATH="/tmp/dev_rendered.yaml"
+sed -E \
+ -e "s#^(\\s*admin_api_base:) .*#\\1 \"http://${SFTPGO_IP}:8080/api/v2\"#g" \
+ -e "/^ sftpgo:/,/^ retention:/ s#^(\\s*host:) .*#\\1 \"127.0.0.1\"#g" \
+ "${ROOT_DIR}/configs/dev.yaml" >"${RENDERED_CFG_HOST_PATH}"
+docker cp "${RENDERED_CFG_HOST_PATH}" "${HEAD_CONTAINER}:/tmp/dev_rendered.yaml"
+CONFIG_IN_CONTAINER="/tmp/dev_rendered.yaml"
echo "[host] verify head discovery record (supervised in-container)"
HEAD_IP_FILE="${SHARED_ROOT}/ray/discovery/${CLUSTER_NAME}/head.json"
@@ -224,14 +232,7 @@ dexec "${HEAD_CONTAINER}" bash -lc "set -euo pipefail; \
(cp -f /private/common/datasets/gsm8k_sft/train.parquet '/private/users/${USER_ID}/datasets/gsm8k_sft/train.parquet' 2>/dev/null || cp -f /private/datasets/gsm8k_sft/train.parquet '/private/users/${USER_ID}/datasets/gsm8k_sft/train.parquet' 2>/dev/null || true); \
(cp -f /private/common/datasets/gsm8k_sft/test.parquet '/private/users/${USER_ID}/datasets/gsm8k_sft/test.parquet' 2>/dev/null || cp -f /private/datasets/gsm8k_sft/test.parquet '/private/users/${USER_ID}/datasets/gsm8k_sft/test.parquet' 2>/dev/null || true)"
-echo "[host] resolve local model snapshot path (avoid HF mirror 429 for vllm rollout)"
-LOCAL_MODEL_PATH="$(dexec "${HEAD_CONTAINER}" bash -lc "python3 - <<'PY'\nimport os\nfrom huggingface_hub import snapshot_download\nmodel_id=os.environ.get('MODEL_ID','Qwen/Qwen2.5-0.5B-Instruct')\nos.environ.setdefault('HF_HOME','/private/hf')\ntry:\n p=snapshot_download(repo_id=model_id, local_files_only=True)\n print(p)\nexcept Exception as e:\n raise SystemExit(f'ERROR: model snapshot not in cache; run 30_prepare_data_and_model.sh first. {e!r}')\nPY\n" MODEL_ID='Qwen/Qwen2.5-0.5B-Instruct' | tail -n 1)"
-if [[ -z "${LOCAL_MODEL_PATH}" || "${LOCAL_MODEL_PATH}" != /* ]]; then
- echo "ERROR: failed to resolve LOCAL_MODEL_PATH: ${LOCAL_MODEL_PATH}" >&2
- exit 1
-fi
-echo "[host] local_model_path: ${LOCAL_MODEL_PATH}"
-
+LOCAL_MODEL_PATH="Qwen/Qwen2.5-0.5B-Instruct"
echo "[host] submit PPO/GRPO/SFT via API using user dataset paths"
PPO_TASK_ID="$(submit_taskspec_inline "${USER_TOKEN}" $'workload: ppo\nnnodes: 2\nn_gpus_per_node: 4\ncode_path: /private/common/code/verl/verl_repo\ntrain_file: /private/users/'"${USER_ID}"$'/datasets/gsm8k/train.parquet\nval_file: /private/users/'"${USER_ID}"$'/datasets/gsm8k/test.parquet\nmodel_id: '"${LOCAL_MODEL_PATH}"$'\ntotal_epochs: 1\ntotal_training_steps: 10\nsave_freq: 10\n')"
GRPO_TASK_ID="$(submit_taskspec_inline "${USER_TOKEN}" $'workload: grpo\nnnodes: 2\nn_gpus_per_node: 4\ncode_path: /private/common/code/verl/verl_repo\ntrain_file: /private/users/'"${USER_ID}"$'/datasets/gsm8k/train.parquet\nval_file: /private/users/'"${USER_ID}"$'/datasets/gsm8k/test.parquet\nmodel_id: '"${LOCAL_MODEL_PATH}"$'\ntotal_epochs: 1\ntotal_training_steps: 10\nsave_freq: 10\n')"
diff --git a/walkthrough.md b/walkthrough.md
new file mode 100644
index 0000000..3427b9c
--- /dev/null
+++ b/walkthrough.md
@@ -0,0 +1,27 @@
+# 源码走读
+## API Server
+API Server是平台服务入口，提供API和web UI功能。
+
+- 入口：src/mvp/py/server.py
+- 配置文件：src/mvp/configs/dev.yaml，解析成V2Config数据结构
+- 核心模块：
+ - service：服务层，包括API服务，任务调度，模型调度等后台任务
+ - core： 核心数据结构，任务ID，submission ID，model serving ID定义
+ - ray： 对接ray cluster的client
+
+## service核心模块
+API Server核心模块包括：
+- app.py: API 入口层，提供webui，将API请求转化为各类数据库操作，以及协调SFTPGo服务
+- scheduler.py：定时任务，调度训练任务队列，提交ray job，更新数据库中任务状态
+- serving_reconciler.py: 定时任务，模型推理调度，提交ray serve app，调整副本数，更新数据库中模型实例状态
+- db.py: 数据库操作基础工具类
+- janitor.py：定时清理训练任务中间过程数据
+- sftpgo.py: 对接SFTPGo的客户端，创建用户、重置密码、初始化用户目录等
+
+## core核心模块
+- ray_job_tool.py：通过builder模板构建ray job命令，提交ray job到ray集群。
+- head_publisher.py: Ray head节点自动写head IP 文件到共享存储
+- worker_watchdog.py: 自动检查最新head IP文件，加入head的ray集群。
+- models: 定义RayConfig/JobSepc/AdvancedTaskSpec等核心数据结构
+
+