dsh-scnet 0.2.0 → 0.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +15 -1
  2. package/package.json +1 -1
  3. package/skills/scnet-hpc/clusters/wuzhshell.conf +60 -0
package/README.md CHANGED
@@ -24,6 +24,14 @@ git 源、本地目录安装以及验证步骤见 [INSTALL.md](./INSTALL.md)。
24
24
  |---|---|
25
25
  | scnet-hpc | 国产超算使用规范：连接、提交/监控、调试、失败排查、海光 DCU/DTK 资源索引 |
26
26
 
27
+ ### 内置集群
28
+
29
+ | 短名 | 描述 | 加速器 |
30
+ |---|---|---|
31
+ | zzeshell | 超算互联网 · 郑州 | 海光 BW1000 DCU (gfx936) ×8, 64GB/卡 |
32
+ | kseshell | 超算互联网 · 昆山 | 海光 Z100 DCU (gfx906) ×4, 16GB/卡 |
33
+ | wuzhshell | 超算互联网 · 乌镇 | 海光 Z100 DCU (gfx906) ×4, 16GB/卡 |
34
+
27
35
  ### Tools
28
36
 
29
37
  | 工具 | 说明 |
@@ -48,7 +56,13 @@ git 源、本地目录安装以及验证步骤见 [INSTALL.md](./INSTALL.md)。
48
56
  ├── package.json # dsh.bundle + dsh.skills
49
57
  ├── cordis.patch.yml # bundle 组合层
50
58
  ├── index.mjs # Cordis 入口，注册 7 个工具
51
- ├── skills/scnet-hpc/ # Agent Skill + clusters/scripts/references
59
+ ├── skills/scnet-hpc/
60
+ │ ├── clusters/
61
+ │ │ ├── zzeshell.conf
62
+ │ │ ├── kseshell.conf
63
+ │ │ └── wuzhshell.conf
64
+ │ ├── scripts/
65
+ │ └── references/
52
66
  ├── sync.sh # 从 canonical 仓库同步
53
67
  ├── README.md # 项目说明
54
68
  ├── INSTALL.md # 安装与验证
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "dsh-scnet",
3
- "version": "0.2.0",
3
+ "version": "0.2.1",
4
4
  "description": "DeepSeek Harness bundle plugin for SCNet (scnet.cn) and similar domestic HPC clusters: SSH setup, Slurm job generation, cluster probing/refresh, compute-node capability probes, and Hygon DCU/DTK guidance.",
5
5
  "type": "module",
6
6
  "main": "./index.mjs",
package/skills/scnet-hpc/clusters/wuzhshell.conf ADDED
@@ -0,0 +1,60 @@
1
+ # wuzhshell —— 乌镇超算（wuzh02.hpccube.com）
2
+
3
+ # ---- 连接 ----
4
+ CLUSTER_ID="wuzhshell"
5
+ CLUSTER_DESC="乌镇超算（wuzh02）"
6
+ SSH_HOST="wuzh02.hpccube.com"
7
+ SSH_PORT="65091"
8
+ HOME_BASE="/work/home"
9
+
10
+ KEY_NAME_MARKER="_<CLUSTER_HOST>_"
11
+ NEEDS_UPDATE_HOSTKEYS_NO="no"
12
+
13
+ # ---- 调度器 ----
14
+ SCHEDULER="slurm"
15
+
16
+ # 默认使用 DCU 队列；纯 CPU 作业改用 wzhcnormal。
17
+ PARTITION="wzhdnormal"
18
+
19
+ DEF_MEM_PER_CPU="3634"
20
+ MIN_GRES="dcu:1"
21
+ GRES_TYPE="dcu"
22
+ MAX_WALLTIME="333-08:00:00"
23
+
24
+ # CPU 队列和 DCU 队列。
25
+ PARTITION_CPU="wzhcnormal"
26
+ PARTITION_DCU="wzhdnormal"
27
+
28
+ # ---- 硬件 ----
29
+ ACCEL_NAME="海光 Z100 DCU (Z100SM)"
30
+ ACCEL_ARCH="gfx906"
31
+ ACCEL_PER_NODE="4"
32
+ ACCEL_MEM_GB="16"
33
+ CPUS_PER_NODE="32"
34
+ CPU_MODEL="Hygon C86 7285 32-core Processor"
35
+ NODE_MEM_GB="123"
36
+ NODE_COUNT="434"
37
+ LOGIN_NODES="login01 / login02（示意）"
38
+ HOME_QUOTA_GB="2000"
39
+
40
+ # ---- 软件栈 ----
41
+ TOOLCHAIN="DTK"
42
+ TOOLCHAIN_VERSION="26.04"
43
+ TOOLCHAIN_PATH=""
44
+ MODULE_LOADS="compiler/dtk/26.04"
45
+ PYTHON_MODULE="python/3.8.10"
46
+
47
+ DEFAULT_VENV=""
48
+
49
+ # ---- 网络 ----
50
+ NET_OK="pypi.org pypi.tuna.tsinghua.edu.cn modelscope.cn github.com"
51
+ NET_BLOCKED="huggingface.co"
52
+ PIP_INDEX="https://pypi.tuna.tsinghua.edu.cn/simple"
53
+ COMPUTE_NODE_OFFLINE="yes"
54
+ TMP_SHARED="no"
55
+
56
+ # ---- 已知问题 ----
57
+ LOGIN_NODE_MISSING_LIBS=""
58
+ KNOWN_LIMITATIONS="gfx906 (Vega20) 无 FP8/BF16 硬件支持、无 MFMA Matrix Core；\
59
+ 单卡显存 16GB；计算节点默认无 torch（module load compiler/dtk/26.04 后仍无 torch，需建 venv）；\
60
+ 计算节点无外网（PROBE_NET_PYPI=OFFLINE）；DCU FP8/Triton/bitsandbytes 待装 torch 后实测"