fix: 推理/评测结果同步、数据集统计与算力节点管理增强
后端: - 抽取 fetch_eval_result_content 复用函数,model_eval_detail 直接应用评测任务结果 - health 接口移除数据库依赖,返回静态指标 - 数据集: count_dataset_records JSON 感知计数; 文件统计改为从 dataset_files 聚合重算; 在线编辑记录 size/record_count/version_no; 上传同步批处理 - 算力节点: 调度支持 requested GPU 子集校验与容量计算; 新增 delete_compute_node(含活动任务保护)及 DELETE 接口; 连接池 connect_timeout - 评测任务落库 basic_metrics/score/completed_time, failed/stopped 记录 error 评测引擎: - _load_dataset 支持 JSON/JSONL 文件 - 新增 exact match 与文本相似度指标, 余弦相似度去掉 2 样本限制 前端: - 算力节点列表「维护」改为「删除」(带确认弹窗), compute.ts 新增 deleteComputeNode - 数据集上传超时调整为 120s; FineTuneTask 增加 compute_node_id; GpuInfo 状态增加 reserved
This commit is contained in:
@@ -1,7 +1,6 @@
|
||||
from fastapi import APIRouter
|
||||
|
||||
from app.core.logging import get_logger
|
||||
from app.db.platform_store import get_platform_store
|
||||
|
||||
router = APIRouter()
|
||||
logger = get_logger(__name__)
|
||||
@@ -10,5 +9,9 @@ logger = get_logger(__name__)
|
||||
@router.get("/health")
|
||||
async def health_check() -> dict[str, object]:
|
||||
logger.info("health check requested")
|
||||
return {"code": 0, "message": "ok", "data": get_platform_store().health_metrics()}
|
||||
return {
|
||||
"code": 0,
|
||||
"message": "ok",
|
||||
"data": {"cpu_percent": 0.0, "memory_percent": 0.0, "disk_percent": 0.0},
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user