d72dbff689
- 新增 P 组(prefill)/D 组(decode) deploy profiles（mooncake RDMA + 计算网 mlx5_0~3） - 新增 experiments/pro6000/kimi3_pro6000_pd_rdma/ 编排脚本（mc-master+P+D+router） - 关键修复: 必须关闭 PYTORCH_CUDA_ALLOC_CONF=expandable_segments （mooncake RDMA 注册 expandable GPU 段报 Bad address，GitHub #2511） - 容器内升级 mooncake 0.3.12.post1（含 dmabuf 修复 #2035） - docs/KIMI_K3_DEPLOY.md 新增附录 B，README 更新实验索引
31 lines
1.2 KiB
Bash
Executable File
31 lines
1.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Kimi-K3 PD 分离部署（MoonCake RDMA）实验配置。
|
||
# 服务器生命周期走 deploy_pd.sh 编排脚本 + deploy profiles：
|
||
# - P 组 profile: pro6000/kimi3_pro6000_pd_prefill
|
||
# - D 组 profile: pro6000/kimi3_pro6000_pd_decode
|
||
# - 编排: experiments/pro6000/kimi3_pro6000_pd_rdma/deploy_pd.sh
|
||
# 部署参数以 profile / deploy_pd.sh 为准，勿在此重复。
|
||
|
||
EXPERIMENT="kimi3_pro6000_pd_rdma"
|
||
MODEL_NAME="Kimi-K3"
|
||
MODEL_PATH="/data/hf_models/Kimi-K3"
|
||
SERVED_MODEL_NAME="kimi-k3"
|
||
|
||
# Router (MiniLB) 入口端口。
|
||
SGLANG_PORT="${SGLANG_PORT:-31000}"
|
||
|
||
# MoonCake master 地址（P 组头节点）。
|
||
MOONCAKE_MASTER="${MOONCAKE_MASTER:-174.1.60.1:50051}"
|
||
|
||
# Python interpreter for orchestration scripts.
|
||
VENV_CLIENT="${VENV_CLIENT:-/root/miniconda3/envs/mas}"
|
||
|
||
# Run the benchmark client natively (0) or inside Docker (1).
|
||
USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-1}"
|
||
|
||
# Deployment profiles used by deploy_pd.sh.
|
||
P_DEPLOY_PROFILE="${P_DEPLOY_PROFILE:-pro6000/kimi3_pro6000_pd_prefill}"
|
||
D_DEPLOY_PROFILE="${D_DEPLOY_PROFILE:-pro6000/kimi3_pro6000_pd_decode}"
|
||
|
||
# Per-scenario timeout to avoid hangs (seconds).
|
||
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-3600}" |