64 lines
1.7 KiB
YAML
64 lines
1.7 KiB
YAML
# Dynin-Omni 3-stage deploy with cross-node connectors (Mooncake demo).
|
|
#
|
|
# Topology is frozen in models/dynin_omni/pipeline.py (``pipeline: dynin_omni``).
|
|
# This variant wires a MooncakeConnector for each stage hand-off in place of
|
|
# the default SharedMemoryConnector. Update the ``extra`` host/master/metadata
|
|
# fields to match your Mooncake deployment before use.
|
|
pipeline: dynin_omni
|
|
async_chunk: false
|
|
trust_remote_code: false
|
|
enable_prefix_caching: false
|
|
|
|
connectors:
|
|
# Mooncake connector for cross-node/intra-node communication.
|
|
mooncake_connector:
|
|
name: MooncakeConnector
|
|
extra:
|
|
host: "127.0.0.1"
|
|
metadata_server: "http://10.90.67.86:8080/metadata"
|
|
master: "10.90.67.86:50051"
|
|
segment: 512000000 # 512MB
|
|
localbuf: 64000000 # 64MB
|
|
proto: "tcp"
|
|
|
|
# Yuanrong connector for cross-node/intra-node communication.
|
|
yuanrong_connector:
|
|
name: YuanrongConnector
|
|
extra:
|
|
host: "127.0.0.1"
|
|
port: "35000"
|
|
|
|
# Alternative SHM connector with an explicit threshold.
|
|
shared_memory_connector:
|
|
name: SharedMemoryConnector
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
devices: "0"
|
|
max_num_seqs: 1
|
|
max_num_batched_tokens: 32768
|
|
enforce_eager: true
|
|
async_scheduling: false
|
|
output_connectors:
|
|
to_stage_1: mooncake_connector
|
|
|
|
- stage_id: 1
|
|
devices: "0"
|
|
max_num_seqs: 1
|
|
max_num_batched_tokens: 32768
|
|
enforce_eager: true
|
|
async_scheduling: false
|
|
input_connectors:
|
|
from_stage_0: mooncake_connector
|
|
output_connectors:
|
|
to_stage_2: mooncake_connector
|
|
|
|
- stage_id: 2
|
|
devices: "0"
|
|
max_num_seqs: 1
|
|
max_num_batched_tokens: 32768
|
|
enforce_eager: true
|
|
async_scheduling: false
|
|
input_connectors:
|
|
from_stage_1: mooncake_connector
|