- sskj.deploy runtime 支持 NODE_HOSTS 多节点编排(ssh 分发/本地 rank/LOCAL_NODE_RANK)
与 ENGINE=vllm 启动(SERVER_CMD),容器名按 rank 自动唯一
- scripts/common/deploy_cli.sh 新增 deploy_stop/status/multinode helper 与 node-rank 透传
- src/sskj/common/env.py 修复嵌套 ${VAR:-${OTHER}/path} 展开(平衡花括号扫描)
- deploy/profiles/pro6000/ 新增 6 个 profile: tp16/tp16_eagle/glm52(多节点)、
sglang/vllm tp_dp_matrix、qwen3(单节点)
- 6 个实验 start/stop 脚本改为 deploy 薄包装,run_bench/adaptive 的 server 启停走
deploy_render_args/deploy_start/deploy_stop,tp16 新增 matrix.json
- 首次入库 glm52_pro6000_sglang_multinode_tp16 实验目录;ops/README.md 补 pro6000 章节
- 实测通过: 单节点 dsv4 sglang/vllm 链路 + tp16 双节点启动/bench/清理
128 lines
2.2 KiB
JSON
128 lines
2.2 KiB
JSON
{
|
|
"comment": "ISL/OSL matrix for dsv4_pro6000_sglang_tp16 (multi-node TP16 EP2). Y=must test, P=optional, N=skip. Extracted from run_batch.sh legacy inline matrix; concurrency per ISL mirrors get_conc_for().",
|
|
"mode": "Y",
|
|
"matrix": {
|
|
"1024": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"4096": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"8192": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "Y"
|
|
},
|
|
"16384": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "P"
|
|
},
|
|
"32768": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "Y",
|
|
"4096": "P"
|
|
},
|
|
"65536": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "Y",
|
|
"2048": "P",
|
|
"4096": "N"
|
|
},
|
|
"131072": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "Y",
|
|
"1024": "P",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
},
|
|
"262144": {
|
|
"128": "Y",
|
|
"256": "Y",
|
|
"512": "P",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
},
|
|
"524288": {
|
|
"128": "Y",
|
|
"256": "P",
|
|
"512": "N",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
},
|
|
"1048576": {
|
|
"128": "Y",
|
|
"256": "P",
|
|
"512": "N",
|
|
"1024": "N",
|
|
"2048": "N",
|
|
"4096": "N"
|
|
}
|
|
},
|
|
"concurrency": {
|
|
"1024": {
|
|
"low": 1,
|
|
"high": 128
|
|
},
|
|
"4096": {
|
|
"low": 1,
|
|
"high": 128
|
|
},
|
|
"8192": {
|
|
"low": 1,
|
|
"high": 32
|
|
},
|
|
"16384": {
|
|
"low": 1,
|
|
"high": 32
|
|
},
|
|
"32768": {
|
|
"low": 1,
|
|
"high": 8
|
|
},
|
|
"65536": {
|
|
"low": 1,
|
|
"high": 8
|
|
},
|
|
"131072": {
|
|
"low": 1,
|
|
"high": 4
|
|
},
|
|
"262144": {
|
|
"low": 1,
|
|
"high": 4
|
|
},
|
|
"524288": {
|
|
"low": 1,
|
|
"high": 4
|
|
},
|
|
"1048576": {
|
|
"low": 1,
|
|
"high": 4
|
|
}
|
|
}
|
|
} |