0c39f2f5b9
算力节点 (compute): - 新建 eval_runner.py: 评测执行引擎，作为subprocess运行 - 加载模型 + JSONL数据集 + 逐样本推理 - BLEU/ROUGE/Cosine基础指标计算 - LLM Judge评分(OpenAI兼容API调用) - 结果写入eval_results.json - adapter.py: build_command新增engine=eval分支 - main.py: 新增/json模块导入，新增/compute/files/read端点，eval job校验 后端: - platform.py: 重写startEval提交eval job到算力节点 - 支持models表和trained_models表查找 - 已合并模型不传adapter路径 - platform_store.py: 新增update_eval_task/running_eval_tasks/apply_eval_job_result - sync.py: poller新增eval job同步，异步读取eval_results.json回写结果 前端: - EvalCreateView/DimensionCreateView: eval模型过滤扩展(API类型+api_url) - EvalCreateView: GPU过滤在线节点空闲GPU - EvalTaskSetupStep: GPU value从数组index改为gpu.id - BasicMetricSetupStep: ROUGE方法名修正(rouge_1→rouge1) - EvalView: 新增5秒轮询刷新 Co-Authored-By: Claude <noreply@anthropic.com>
93 lines
4.7 KiB
Python
93 lines
4.7 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from app.db.platform_store import get_platform_store
|
|
from app.modules.compute_gateway.client import ComputeNodeClient
|
|
|
|
|
|
def _node_for_task(task: dict[str, Any]) -> dict[str, Any] | None:
|
|
return next((node for node in get_platform_store().compute_nodes() if node["id"] == task.get("compute_node_id")), None)
|
|
|
|
|
|
async def poll_compute_jobs_once() -> dict[str, Any]:
|
|
store = get_platform_store()
|
|
synced: list[dict[str, Any]] = []
|
|
failed: list[dict[str, str]] = []
|
|
for task in store.running_compute_tasks():
|
|
node = _node_for_task(task)
|
|
if not node:
|
|
failed.append({"task_id": task["id"], "error": "compute node not found"})
|
|
continue
|
|
try:
|
|
client = ComputeNodeClient(node["api_base_url"])
|
|
job = await client.get_job(task["compute_job_id"])
|
|
try:
|
|
logs = await client.job_logs(task["compute_job_id"], tail_lines=5000)
|
|
store.record_training_log_metrics(task["id"], str(logs.get("content") or ""))
|
|
except Exception:
|
|
pass
|
|
# P0-4: Force-fetch last log snippet when job reaches terminal state
|
|
if job.get("status") in {"failed", "stopped"}:
|
|
try:
|
|
last_logs = await client.job_logs(task["compute_job_id"], tail_lines=200)
|
|
job["log_snippet"] = str(last_logs.get("content") or "")[:8192]
|
|
except Exception:
|
|
pass
|
|
synced.append(store.apply_compute_job(task["id"], job))
|
|
except Exception as exc: # noqa: BLE001 - keep polling other jobs
|
|
failed.append({"task_id": task["id"], "error": str(exc)})
|
|
standalone_synced: list[dict[str, Any]] = []
|
|
for record in store.active_standalone_compute_jobs():
|
|
node = next((item for item in store.compute_nodes() if item["id"] == record.get("node_id")), None)
|
|
if not node:
|
|
failed.append({"job_id": record["id"], "error": "compute node not found"})
|
|
continue
|
|
try:
|
|
job = await ComputeNodeClient(node["api_base_url"]).get_job(record["id"])
|
|
standalone_synced.append(store.sync_model_merge_job(record["id"], job))
|
|
except Exception as exc: # noqa: BLE001 - keep polling other jobs
|
|
failed.append({"job_id": record["id"], "error": str(exc)})
|
|
|
|
# ── Eval job sync ────────────────────────────────────────────────
|
|
eval_synced = 0
|
|
for eval_task in store.running_eval_tasks():
|
|
node = next(
|
|
(item for item in store.compute_nodes() if item["id"] == eval_task.get("compute_node_id")),
|
|
None,
|
|
)
|
|
if not node:
|
|
failed.append({"eval_task_id": eval_task["id"], "error": "compute node not found"})
|
|
continue
|
|
try:
|
|
client = ComputeNodeClient(node["api_base_url"])
|
|
job = await client.get_job(eval_task["compute_job_id"])
|
|
result_content = None
|
|
# Try to read eval_results.json from the job output directory
|
|
if job.get("status") == "completed" and job.get("output_dir"):
|
|
try:
|
|
full_path = f"{job['output_dir'].rstrip('/')}/eval_results.json"
|
|
# Convert absolute path to relative (strip YG_FT_DATA_ROOT prefix)
|
|
data_root = "/data/yg-ft/"
|
|
if full_path.startswith(data_root):
|
|
full_path = full_path[len(data_root):]
|
|
rel_path = full_path.lstrip("/")
|
|
import httpx
|
|
settings_path = f"{node['api_base_url'].rstrip('/')}/modelTF/compute/files/read"
|
|
async with httpx.AsyncClient(timeout=30, headers=client.headers()) as http:
|
|
read_resp = await http.get(settings_path, params={"path": rel_path})
|
|
if read_resp.status_code == 200:
|
|
result_content = read_resp.json()
|
|
except Exception:
|
|
pass
|
|
store.apply_eval_job_result(eval_task["id"], job, result_content)
|
|
# If job completed, un-mark inference loaded
|
|
if job.get("status") in {"completed", "failed", "stopped"}:
|
|
store.mark_inference_unloaded(node["id"])
|
|
eval_synced += 1
|
|
except Exception as exc: # noqa: BLE001
|
|
failed.append({"eval_task_id": eval_task["id"], "error": str(exc)})
|
|
|
|
return {"synced": len(synced) + len(standalone_synced) + eval_synced, "failed": failed,
|
|
"items": synced, "standalone": standalone_synced, "eval_synced": eval_synced}
|