- 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
41 lines
1.4 KiB
Bash
Executable File
41 lines
1.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Start SGLang multi-node TP=16 EP=2 across 2 nodes through the shared
|
|
# deployment layer (`python -m sskj.deploy start`, NODE_HOSTS orchestration).
|
|
# Usage: start_sglang_multinode.sh [--dry-run]
|
|
set -Eeuo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/config.env"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../../scripts/common/deploy_cli.sh"
|
|
|
|
RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
|
|
mkdir -p "${RUNTIME_BASE}/logs"
|
|
|
|
DRY_RUN="${DRY_RUN:-0}"
|
|
DEPLOY_PROFILE="${DEPLOY_PROFILE:-pro6000/dsv4_pro6000_sglang_tp16}"
|
|
|
|
log "=== SGLang multi-node TP=${TP_SIZE} EP=${EP_SIZE} via deploy profile ${DEPLOY_PROFILE} ==="
|
|
|
|
if [[ "$DRY_RUN" == "1" ]]; then
|
|
PYTHONPATH="${ROOT_DIR}/src" "${DEPLOY_PYTHON:-python3}" -m sskj.deploy start \
|
|
--profile "$(deploy_profile_abs "$DEPLOY_PROFILE")" \
|
|
--tp "$TP_SIZE" --dp "1" \
|
|
--port "${SGLANG_PORT:-30000}" \
|
|
--model-path "$MODEL_PATH" \
|
|
--log-dir "${RUNTIME_BASE}/logs" \
|
|
--dry-run
|
|
else
|
|
deploy_start_multinode \
|
|
"$DEPLOY_PROFILE" "$TP_SIZE" "1" \
|
|
"${RUNTIME_BASE}/logs" \
|
|
"${SGLANG_PORT:-30000}" \
|
|
"$MODEL_PATH" \
|
|
"$EXPERIMENT"
|
|
fi
|