Files
vllm-omni/vllm_omni/deploy/hunyuan-image-3-mooncakeconnector.yaml
T
102ba716bf [Feat] Add native Mooncake KV transfer from AR to DiT (#7166)
Signed-off-by: asukaqaq-s <1311722138@qq.com>
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-09-20 14:44:55 +00:00

83 lines
2.2 KiB
YAML

pipeline: hunyuan_image_3_moe
async_chunk: false
trust_remote_code: true
stages:
- stage_id: 0
is_comprehension: true
# Return AR text (including CoT) alongside the final image.
final_output: true
final_output_type: text
num_replicas: 2
devices: "0,1,2,3"
tensor_parallel_size: 2
max_num_seqs: 1
max_num_batched_tokens: 32768
kv_cache_memory_bytes: 2147483648
gpu_memory_utilization: 0.95
enforce_eager: true
moe_backend: triton
env:
MC_TCP_ENABLE_CONNECTION_POOL: "1"
MC_TCP_SLICE_SIZE: "4194304"
VLLM_USE_FLASHINFER_SAMPLER: "0"
hf_overrides:
rope_parameters:
mrope_section: [0, 32, 32]
rope_type: default
kv_transfer_config:
kv_connector: MooncakeConnector
kv_role: kv_producer
engine_id: hunyuan-image3-ar
kv_ip: 127.0.0.1
kv_connector_extra_config:
mooncake_protocol: tcp
bootstrap_port: 8998
default_sampling_params:
temperature: 0.0
max_tokens: 8192
detokenize: true
skip_special_tokens: false
include_stop_str_in_output: true
- stage_id: 1
num_replicas: 2
devices: "4,5,6,7"
max_num_seqs: 1
max_num_batched_tokens: 16384
max_model_len: 12288
kv_cache_memory_bytes: 1073741824
enforce_eager: true
# Registered Mooncake KV pages must remain mapped for the connector lifetime.
enable_sleep_mode: false
moe_backend: triton
env:
MC_TCP_ENABLE_CONNECTION_POOL: "1"
MC_TCP_SLICE_SIZE: "4194304"
PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
distributed_executor_backend: mp
diffusion_kv_mode: paged_scheduler
diffusion_kv_max_rows_per_request: 2
kv_transfer_config:
kv_connector: MooncakeConnector
kv_role: kv_consumer
engine_id: hunyuan-image3-dit
kv_connector_extra_config:
mooncake_protocol: tcp
# Seconds to wait before failing a request; in-flight pages remain reserved.
transfer_timeout: 60.0
parallel_config:
tensor_parallel_size: 2
enable_expert_parallel: true
default_sampling_params:
num_inference_steps: 2
guidance_scale: 2.0
height: 512
width: 512
edges:
- from: 0
to: 1
window_size: -1
max_inflight: 1