[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)

Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-07-18 09:34:33 +00:00
1 parent 793d3e9ab7
commit 4fbbdfd250
41 files changed
+520 -516

No files matched your search

+18
View File
@@ -0,0 +1,18 @@
# HunyuanVideo-1.5 deploy.
#
# Single GPU by default. Increase tensor_parallel_size and devices for multi-GPU TP.
async_chunk: false
trust_remote_code: true
distributed_executor_backend: mp
stages:
- stage_id: 0
devices: "0"
max_num_seqs: 1
tensor_parallel_size: 1
enforce_eager: true
# HunyuanVideo-1.5 peak VRAM is dominated by the single-shot VAE decode of
# the full video, so tiling the decode is the main memory lever.
vae_use_tiling: true
default_sampling_params:
seed: 42
+39
View File
@@ -0,0 +1,39 @@
# Step-Audio2 deploy: thinker -> token2wav.
#
# Sequential mode waits for the full Thinker output before running Token2Wav.
async_chunk: false
trust_remote_code: true
enable_prefix_caching: false
stages:
- stage_id: 0
devices: "0,1"
tensor_parallel_size: 2
max_num_seqs: 1
gpu_memory_utilization: 0.7
enforce_eager: true
async_scheduling: false
max_num_batched_tokens: 8192
default_sampling_params:
temperature: 0.7
top_p: 0.9
top_k: -1
max_tokens: 1024
seed: 42
repetition_penalty: 1.05
- stage_id: 1
devices: "1"
max_num_seqs: 1
gpu_memory_utilization: 0.2
enforce_eager: true
async_scheduling: false
max_num_batched_tokens: 4096
hf_overrides:
architectures: ["StepAudio2Token2WavForConditionalGeneration"]
default_sampling_params:
temperature: 0.0
top_p: 1.0
top_k: -1
max_tokens: 1
seed: 42
+22
View File
@@ -0,0 +1,22 @@
# Step-Audio2 ASR deploy: thinker only.
pipeline: step_audio_2_asr
async_chunk: false
trust_remote_code: true
enable_prefix_caching: false
stages:
- stage_id: 0
devices: "0,1"
tensor_parallel_size: 2
max_num_seqs: 1
gpu_memory_utilization: 0.8
enforce_eager: true
async_scheduling: false
max_num_batched_tokens: 2048
default_sampling_params:
temperature: 0.7
top_p: 0.9
top_k: -1
max_tokens: 1024
seed: 42
repetition_penalty: 1.05
@@ -0,0 +1,37 @@
# Step-Audio2 deploy: thinker -> token2wav with async chunk streaming.
async_chunk: true
trust_remote_code: true
enable_prefix_caching: false
stages:
- stage_id: 0
devices: "0,1"
tensor_parallel_size: 2
max_num_seqs: 1
gpu_memory_utilization: 0.7
enforce_eager: true
async_scheduling: false
max_num_batched_tokens: 1024
default_sampling_params:
temperature: 0.7
top_p: 0.9
top_k: -1
max_tokens: 1024
seed: 42
repetition_penalty: 1.05
- stage_id: 1
devices: "1"
max_num_seqs: 1
gpu_memory_utilization: 0.2
enforce_eager: true
async_scheduling: false
max_num_batched_tokens: 2048
hf_overrides:
architectures: ["StepAudio2Token2WavForConditionalGeneration"]
default_sampling_params:
temperature: 0.0
top_p: 1.0
top_k: -1
max_tokens: 1
seed: 42
+17
View File
@@ -0,0 +1,17 @@
# Wan2.2 TI2V-5B deploy.
#
# Single GPU by default. Increase tensor_parallel_size and devices for A14B MoE variants.
async_chunk: false
trust_remote_code: true
distributed_executor_backend: mp
stages:
- stage_id: 0
devices: "0"
max_num_seqs: 1
tensor_parallel_size: 1
enforce_eager: true
# Keep VAE tiling on by default for higher resolutions / longer clips.
vae_use_tiling: true
default_sampling_params:
seed: 42