Skip to content

[Misc] fix stage config describe and yaml format #265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hsliuustc0106 merged 3 commits into from
Dec 11, 2025
+17 −17
Merged

[Misc] fix stage config describe and yaml format #265

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0cec58a
fix stage config describe
david6666666 Dec 10, 2025
bf00378
fix stage config describe
david6666666 Dec 10, 2025
accd043
yaml format
david6666666 Dec 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion tests/multi_stages/stage_configs/qwen2_5_omni_ci.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# stage config for running qwen2.5-omni with architecture of OmniLLM.

# The following config has been verified on 1x 24GB GPU (L4/RTX3090).
# The following config has been verified on 2x 24GB GPU (L4/RTX3090/RTX4090).
# This config is optimized for CI e2e tests.
stage_args:
- stage_id: 0
Expand Down
2 changes: 1 addition & 1 deletion vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# stage config for running qwen2.5-omni with architecture of OmniLLM.

# The following config has been verified on 1x H100-80G GPU.
# The following config has been verified on 2x H100-80G GPU.
stage_args:
- stage_id: 0
runtime:
Expand Down
30 changes: 15 additions & 15 deletions vllm_omni/model_executor/stage_configs/qwen3_omni_moe.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,22 +37,22 @@ stage_args:

- stage_id: 1
runtime:
devices: "1"
max_batch_size: 1
devices: "1"
max_batch_size: 1
engine_args:
model_stage: talker
model_arch: Qwen3OmniMoeForConditionalGeneration
worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.3
enforce_eager: true
trust_remote_code: true
engine_output_type: latent # Output codec codes for code2wav
# tensor_parallel_size: 2
enable_prefix_caching: false
max_num_batched_tokens: 32768
distributed_executor_backend: "mp"
hf_config_name: talker_config
model_stage: talker
model_arch: Qwen3OmniMoeForConditionalGeneration
worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.3
enforce_eager: true
trust_remote_code: true
engine_output_type: latent # Output codec codes for code2wav
# tensor_parallel_size: 2
enable_prefix_caching: false
max_num_batched_tokens: 32768
distributed_executor_backend: "mp"
hf_config_name: talker_config
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker
# final_output: true
Expand Down