feat: 模型评测端到端闭环 — EvalRunner引擎 + 算力节点Job执行 + 结果回写

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>
This commit is contained in:
wuyongtao
2026-07-28 19:34:41 +08:00
parent c7c9ed925b
commit 0c39f2f5b9
12 changed files with 903 additions and 17 deletions

View File

@@ -1,5 +1,6 @@
from __future__ import annotations
import json
import os
import math
import hashlib
@@ -449,6 +450,29 @@ def create_app() -> FastAPI:
accelerator_errors, accelerator_warnings, accelerator = _validate_training_accelerator(payload)
errors.extend(accelerator_errors)
warnings.extend(accelerator_warnings)
elif engine == "eval":
# Eval engine: validate model path and dataset path
if not payload.get("model_name_or_path"):
errors.append("model_name_or_path is required for eval")
else:
path_checks.append(_check_path_item({
"name": "model_name_or_path",
"path": payload.get("model_name_or_path", ""),
"type": "any",
"required": True,
}))
if payload.get("dataset_path"):
path_checks.append(_check_path_item({
"name": "dataset_path",
"path": payload.get("dataset_path", ""),
"type": "file",
"required": True,
}))
else:
errors.append("dataset_path is required for eval")
if shutil.which("python") is None:
errors.append("python runtime not found")
elif engine == "smoke":
warnings.append("smoke engine skips model and dataset path checks")
@@ -811,6 +835,22 @@ def create_app() -> FastAPI:
"checksum_sha256": checksum,
}
@app.get(f"{route_prefix}/compute/files/read")
async def read_file(path: str = Query(...)) -> JSONResponse:
"""Read a text file from within YG_FT_DATA_ROOT. Used by the backend
to fetch eval results and other job outputs."""
data_root = Path(os.getenv("YG_FT_DATA_ROOT", "/data/yg-ft"))
target = (data_root / path.lstrip("/\\")).resolve()
if not _path_inside(data_root, target):
raise HTTPException(status_code=400, detail="path must stay inside YG_FT_DATA_ROOT")
if not target.is_file():
raise HTTPException(status_code=404, detail="file not found")
try:
content = target.read_text(encoding="utf-8")
return JSONResponse(json.loads(content) if content.strip().startswith("{") else {"content": content})
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc))
@app.get(f"{route_prefix}/compute/files/{{file_id}}/download")
async def download_file(file_id: str) -> FileResponse:
upload_root = Path(os.getenv("YG_FT_DATA_ROOT", "/data/yg-ft")) / "uploads"