44 lines
1.1 KiB
Bash
44 lines
1.1 KiB
Bash
EXPERIMENT="kimi3_pro6000_pd_pp8_standard"
|
|
|
|
BASE_IMAGE="local/sglang:kimi-k3-sm120-flashinfer-mxfp4-phase5"
|
|
PD_IMAGE="local/sglang:kimi-k3-sm120-flashinfer-mxfp4-pd1"
|
|
MODEL_PATH="/data/hf_models/Kimi-K3"
|
|
SERVED_MODEL_NAME="kimi-k3"
|
|
MOONCAKE_WHEEL="/data/flashkda_deploy/wheels/mooncake_transfer_engine_cuda13-0.3.12.post1-cp312-cp312-manylinux_2_28_x86_64.whl"
|
|
|
|
SSH_USER="user"
|
|
SSH_OPTIONS=(-o BatchMode=yes -o StrictHostKeyChecking=no -o ConnectTimeout=10)
|
|
P_NODES=(174.1.60.1 174.1.60.2 174.1.60.3 174.1.60.4)
|
|
D_NODES=(174.1.60.5 174.1.60.6 174.1.60.7 174.1.60.8)
|
|
ALL_NODES=("${P_NODES[@]}" "${D_NODES[@]}")
|
|
|
|
P_HEAD="174.1.60.1"
|
|
D_HEAD="174.1.60.5"
|
|
MC_MASTER="174.1.60.1:50051"
|
|
P_DIST_PORT=20000
|
|
D_DIST_PORT=20000
|
|
P_PORT=30000
|
|
D_PORT=30000
|
|
P_BOOTSTRAP_PORT=28800
|
|
ROUTER_HOST="174.1.60.5"
|
|
ROUTER_PORT=31000
|
|
|
|
P_TP=4
|
|
P_PP=8
|
|
P_EP=4
|
|
P_CHUNKED_PREFILL_SIZE=8192
|
|
P_PAGE_SIZE=64
|
|
P_MEM_FRACTION_STATIC=0.88
|
|
P_MAMBA_FULL_MEMORY_RATIO=0.36
|
|
|
|
D_TP=32
|
|
D_PP=1
|
|
D_EP=32
|
|
D_PAGE_SIZE=64
|
|
D_MEM_FRACTION_STATIC=0.88
|
|
D_MAMBA_FULL_MEMORY_RATIO=0.21
|
|
|
|
HEALTH_WAIT_S=2400
|
|
DISAGG_IB_DEVICES="mlx5_0,mlx5_1,mlx5_2,mlx5_3"
|
|
NCCL_IB_HCAS="mlx5_0,mlx5_1,mlx5_2,mlx5_3"
|