submit next batch of ppu_zw_810e (360 models, supersedes stuck v1.0.28 build)

submit next batch of ppu_zw_810e (250 models); refresh AUTH_TOKEN
submit next batch of ppu_zw_810e (300 models)
2026-08-18 15:34:19 +08:00 · 2026-08-18 11:13:33 +08:00 · 2026-08-13 16:56:17 +08:00 · 2026-08-11 14:30:02 +08:00 · 2026-08-10 17:07:48 +08:00 · 2026-08-07 11:23:46 +08:00
4 changed files with 1192 additions and 81 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,2 @@
+.DS_Store
+__pycache__/
--- a/1
+++ b/1
@@ -2,6 +2,7 @@ FROM modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim

 ENV PYTHONUNBUFFERED=1 
    
+
 WORKDIR /app

 COPY requirements.txt .
--- a/README.md
+++ b/README.md
@@ -1,5 +1,29 @@
 # xc_validation_strategy

-信创自动化模型适配平台 — 验证策略服务
+批量向 ModelHub XC 平台提交模型验证任务的策略服务，之后保持 HTTP 服务存活供平台探活。

-从 HuggingFace 周期性抓取新模型，自动完成同步、下载、提交验证任务的全流程，常驻运行在 xc_agent_platform 上。
+## 功能
+
+- 自动登录 ModelHub 获取 Token
+- 批量提交模型验证任务（vLLM 框架，Cambricon MLU-370-x8）
+- 提交结果写入 `submitted_validation_tasks.txt`
+- 暴露 `/health` 和 `/status` 接口满足平台运行时契约
+
+## 项目结构
+
+```
+.
+├── main.py            # 主入口：HTTP 服务 + 提交逻辑
+├── Dockerfile         # 平台镜像构建配置
+├── requirements.txt   # Python 依赖
+└── submitted_validation_tasks.txt   # 运行后自动生成，记录提交结果
+```
+
+## 平台契约说明
+
+本项目满足平台对策略镜像的全部必要约束：
+
+- Dockerfile 位于仓库根目录，基于官方轻量基础镜像
+- 暴露 8080 端口并实现 `GET /health`
+- 通过环境变量 `STRATEGY_ID` 获取策略 ID
+- 正确处理 `SIGTERM` 信号，支持优雅停机
--- a/main.py
+++ b/main.py
Author	SHA1	Message	Date
zhousha	32122cd866	submit next batch of ppu_zw_810e (360 models, supersedes stuck v1.0.28 build)	2026-08-18 15:34:19 +08:00
zhousha	ebc9f400e0	submit next batch of ppu_zw_810e (250 models); refresh AUTH_TOKEN	2026-08-18 11:13:33 +08:00
zhousha	b546ad980f	submit next batch of ppu_zw_810e (300 models)	2026-08-13 16:56:17 +08:00
zhousha	54adf4f956	submit next batch of ppu_zw_810e (200 models)	2026-08-11 14:30:02 +08:00
zhousha	66f378bdc0	submit next batch of ppu_zw_810e (200 models); refresh AUTH_TOKEN	2026-08-10 17:07:48 +08:00
zhousha	d49bf186ae	submit next batch of ppu_zw_810e (200 models)	2026-08-07 11:23:46 +08:00
zhousha	1b95e92f72	add next batch of ppu_zw_810e submission (500 models, lines 601-1100 of source list)	2026-08-06 13:06:23 +08:00
zhousha	dd9db6b4d2	add ppu_zw_810e submission (600 models), refresh AUTH_TOKEN; skip other 4 GPUs this run	2026-08-04 20:54:10 +08:00
zhousha	5c9f5d9ad7	refresh all 4 GPU model lists with latest filter results	2026-07-29 17:36:02 +08:00
zhousha	9b5087467f	add Kunlunxin_p-800 as 4th GPU with filtered model list	2026-07-29 15:16:34 +08:00
zhousha	7dcada5617	convert to multi-GPU submission (Biren/Cambricon/MetaX) with fresh filtered model lists	2026-07-29 14:26:16 +08:00
zhousha	5958df93b0	switch to Cambricon_mlu-370-x8 with new model list, refresh AUTH_TOKEN	2026-07-27 16:46:41 +08:00
zhousha	a73274e6a4	switch back to ppu_zw_810e with new model list	2026-07-23 14:27:36 +08:00
zhousha	b3c577219f	switch to Biren_166m GPU with new model list	2026-07-22 13:53:23 +08:00
zhousha	1591b3050e	refresh expired AUTH_TOKEN	2026-07-21 18:56:31 +08:00
zhousha	55c77faa70	update model list	2026-07-21 18:42:47 +08:00
zhousha	e51533e0bf	update model list Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-16 16:58:36 +08:00
zhousha	4e603b9fb0	update	2026-07-14 19:06:47 +08:00
zhousha	5fe8bf27e5	update main.py Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-14 18:41:06 +08:00
zhousha	d6b0e416db	update ppu	2026-07-13 19:43:35 +08:00
zhousha	4dcfed6b6d	update ppu	2026-07-13 18:38:55 +08:00
zhousha	1e8cfacd8e	uodate	2026-06-22 19:00:46 +08:00
zhousha	d6cca90496	update main.py	2026-06-22 18:44:42 +08:00
zhousha	031e0dc7a8	update main.py	2026-06-19 01:48:50 +08:00
zhousha	af6f501a5a	update main.py	2026-06-18 15:22:29 +08:00
zhousha	94da35d152	clean up Dockerfile	2026-06-14 23:55:41 +08:00
zhousha	5b92f129d2	clean up Dockerfile	2026-06-14 23:54:02 +08:00
zhousha	87d4ae1c18	fix: add env vars to Dockerfile	2026-06-12 21:02:56 +08:00
zhousha	6f599a8a23	fix: add env vars to Dockerfile	2026-06-12 14:51:50 +08:00