anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Remove obsolete image and YAML configuration files for Qwen2.5 and Qwen3 models from the e2e stage configurations.

Browse Source 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-03-20 02:11:18 +00:00
1 parent 0d23f68997
commit b8f736c5a9
9 files changed
-372
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

image_output.png
BIN
View File
Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 110 KiB

tests/e2e/stage_configs/qwen2_5_omni_ci_1773652593.yaml
-48
View File
@@ -1,48 +0,0 @@
stage_args:
- stage_id: 0
runtime: {process: true, devices: '0', max_batch_size: 1}
engine_args: {model_stage: thinker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.9,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, mm_processor_cache_gb: 0}
is_comprehension: true
final_output: true
final_output_type: text
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 128,
seed: 42, detokenize: true, repetition_penalty: 1.1}
- stage_id: 1
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: talker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.4,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: latent}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen2_5_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_p: 0.8
top_k: 40
max_tokens: 4096
seed: 42
detokenize: true
repetition_penalty: 1.05
stop_token_ids: [8294]
- stage_id: 2
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
gpu_memory_utilization: 0.5, enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: audio, max_num_batched_tokens: 4096, max_model_len: 4096}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 4096,
seed: 42, detokenize: true, repetition_penalty: 1.1}
runtime:
enabled: true
defaults: {window_size: -1, max_inflight: 1}
edges:
- {from: 0, to: 1, window_size: -1}
- {from: 1, to: 2, window_size: -1}
tests/e2e/stage_configs/qwen2_5_omni_ci_1773653262.yaml
-48
View File
@@ -1,48 +0,0 @@
stage_args:
- stage_id: 0
runtime: {process: true, devices: '0', max_batch_size: 1}
engine_args: {model_stage: thinker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.9,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, mm_processor_cache_gb: 0}
is_comprehension: true
final_output: true
final_output_type: text
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 128,
seed: 42, detokenize: true, repetition_penalty: 1.1}
- stage_id: 1
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: talker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.4,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: latent}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen2_5_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_p: 0.8
top_k: 40
max_tokens: 4096
seed: 42
detokenize: true
repetition_penalty: 1.05
stop_token_ids: [8294]
- stage_id: 2
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
gpu_memory_utilization: 0.5, enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: audio, max_num_batched_tokens: 4096, max_model_len: 4096}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 4096,
seed: 42, detokenize: true, repetition_penalty: 1.1}
runtime:
enabled: true
defaults: {window_size: -1, max_inflight: 1}
edges:
- {from: 0, to: 1, window_size: -1}
- {from: 1, to: 2, window_size: -1}
tests/e2e/stage_configs/qwen2_5_omni_ci_1773717276.yaml
-48
View File
@@ -1,48 +0,0 @@
stage_args:
- stage_id: 0
runtime: {process: true, devices: '0', max_batch_size: 1}
engine_args: {model_stage: thinker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.9,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, mm_processor_cache_gb: 0}
is_comprehension: true
final_output: true
final_output_type: text
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 128,
seed: 42, detokenize: true, repetition_penalty: 1.1}
- stage_id: 1
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: talker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.4,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: latent}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen2_5_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_p: 0.8
top_k: 40
max_tokens: 4096
seed: 42
detokenize: true
repetition_penalty: 1.05
stop_token_ids: [8294]
- stage_id: 2
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
gpu_memory_utilization: 0.5, enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: audio, max_num_batched_tokens: 4096, max_model_len: 4096}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 4096,
seed: 42, detokenize: true, repetition_penalty: 1.1}
runtime:
enabled: true
defaults: {window_size: -1, max_inflight: 1}
edges:
- {from: 0, to: 1, window_size: -1}
- {from: 1, to: 2, window_size: -1}
tests/e2e/stage_configs/qwen2_5_omni_ci_1773717938.yaml
-48
View File
@@ -1,48 +0,0 @@
stage_args:
- stage_id: 0
runtime: {process: true, devices: '0', max_batch_size: 1}
engine_args: {model_stage: thinker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.9,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, mm_processor_cache_gb: 0}
is_comprehension: true
final_output: true
final_output_type: text
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 128,
seed: 42, detokenize: true, repetition_penalty: 1.1}
- stage_id: 1
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: talker, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
max_model_len: 16384, max_num_batched_tokens: 16384, max_num_seqs: 1, gpu_memory_utilization: 0.4,
skip_mm_profiling: true, enforce_eager: 'true', trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: latent}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen2_5_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_p: 0.8
top_k: 40
max_tokens: 4096
seed: 42
detokenize: true
repetition_penalty: 1.05
stop_token_ids: [8294]
- stage_id: 2
runtime: {process: true, devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen2_5OmniForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
gpu_memory_utilization: 0.5, enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false,
engine_output_type: audio, max_num_batched_tokens: 4096, max_model_len: 4096}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 4096,
seed: 42, detokenize: true, repetition_penalty: 1.1}
runtime:
enabled: true
defaults: {window_size: -1, max_inflight: 1}
edges:
- {from: 0, to: 1, window_size: -1}
- {from: 1, to: 2, window_size: -1}
tests/e2e/stage_configs/qwen3_omni_ci_1773652593.yaml
-45
View File
@@ -1,45 +0,0 @@
stage_args:
- stage_id: 0
runtime: {devices: '0', max_batch_size: 5}
engine_args: {model_stage: thinker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.9, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
distributed_executor_backend: mp, max_num_batched_tokens: 32768, max_model_len: 32768,
enable_prefix_caching: false, mm_processor_cache_gb: 0, hf_config_name: thinker_config,
tensor_parallel_size: 1, load_format: dummy, custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker_async_chunk}
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params: {temperature: 0.4, top_p: 0.9, top_k: 1, max_tokens: 100,
seed: 42, ignore_eos: false, detokenize: true, repetition_penalty: 1.05}
- stage_id: 1
runtime: {devices: '1', max_batch_size: 5}
engine_args: {model_stage: talker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.5, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, max_num_batched_tokens: 32768, max_model_len: 32768,
distributed_executor_backend: mp, hf_config_name: talker_config, load_format: dummy,
custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav_async_chunk}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_k: 50
max_tokens: 1000
seed: 42
detokenize: false
repetition_penalty: 1.05
stop_token_ids: [2150]
- stage_id: 2
runtime: {devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false, engine_output_type: audio,
gpu_memory_utilization: 0.1, distributed_executor_backend: mp, max_num_batched_tokens: 100000,
hf_config_name: thinker_config, async_scheduling: false, load_format: dummy}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 2000,
seed: 42, detokenize: true, repetition_penalty: 1.1}
async_chunk: true
tests/e2e/stage_configs/qwen3_omni_ci_1773653262.yaml
-45
View File
@@ -1,45 +0,0 @@
stage_args:
- stage_id: 0
runtime: {devices: '0', max_batch_size: 5}
engine_args: {model_stage: thinker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.9, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
distributed_executor_backend: mp, max_num_batched_tokens: 32768, max_model_len: 32768,
enable_prefix_caching: false, mm_processor_cache_gb: 0, hf_config_name: thinker_config,
tensor_parallel_size: 1, load_format: dummy, custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker_async_chunk}
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params: {temperature: 0.4, top_p: 0.9, top_k: 1, max_tokens: 100,
seed: 42, ignore_eos: false, detokenize: true, repetition_penalty: 1.05}
- stage_id: 1
runtime: {devices: '1', max_batch_size: 5}
engine_args: {model_stage: talker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.5, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, max_num_batched_tokens: 32768, max_model_len: 32768,
distributed_executor_backend: mp, hf_config_name: talker_config, load_format: dummy,
custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav_async_chunk}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_k: 50
max_tokens: 1000
seed: 42
detokenize: false
repetition_penalty: 1.05
stop_token_ids: [2150]
- stage_id: 2
runtime: {devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false, engine_output_type: audio,
gpu_memory_utilization: 0.1, distributed_executor_backend: mp, max_num_batched_tokens: 100000,
hf_config_name: thinker_config, async_scheduling: false, load_format: dummy}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 2000,
seed: 42, detokenize: true, repetition_penalty: 1.1}
async_chunk: true
tests/e2e/stage_configs/qwen3_omni_ci_1773717276.yaml
-45
View File
@@ -1,45 +0,0 @@
stage_args:
- stage_id: 0
runtime: {devices: '0', max_batch_size: 5}
engine_args: {model_stage: thinker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.9, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
distributed_executor_backend: mp, max_num_batched_tokens: 32768, max_model_len: 32768,
enable_prefix_caching: false, mm_processor_cache_gb: 0, hf_config_name: thinker_config,
tensor_parallel_size: 1, load_format: dummy, custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker_async_chunk}
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params: {temperature: 0.4, top_p: 0.9, top_k: 1, max_tokens: 100,
seed: 42, ignore_eos: false, detokenize: true, repetition_penalty: 1.05}
- stage_id: 1
runtime: {devices: '1', max_batch_size: 5}
engine_args: {model_stage: talker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.5, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, max_num_batched_tokens: 32768, max_model_len: 32768,
distributed_executor_backend: mp, hf_config_name: talker_config, load_format: dummy,
custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav_async_chunk}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_k: 50
max_tokens: 1000
seed: 42
detokenize: false
repetition_penalty: 1.05
stop_token_ids: [2150]
- stage_id: 2
runtime: {devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false, engine_output_type: audio,
gpu_memory_utilization: 0.1, distributed_executor_backend: mp, max_num_batched_tokens: 100000,
hf_config_name: thinker_config, async_scheduling: false, load_format: dummy}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 2000,
seed: 42, detokenize: true, repetition_penalty: 1.1}
async_chunk: true
tests/e2e/stage_configs/qwen3_omni_ci_1773717938.yaml
-45
View File
@@ -1,45 +0,0 @@
stage_args:
- stage_id: 0
runtime: {devices: '0', max_batch_size: 5}
engine_args: {model_stage: thinker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.9, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
distributed_executor_backend: mp, max_num_batched_tokens: 32768, max_model_len: 32768,
enable_prefix_caching: false, mm_processor_cache_gb: 0, hf_config_name: thinker_config,
tensor_parallel_size: 1, load_format: dummy, custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker_async_chunk}
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params: {temperature: 0.4, top_p: 0.9, top_k: 1, max_tokens: 100,
seed: 42, ignore_eos: false, detokenize: true, repetition_penalty: 1.05}
- stage_id: 1
runtime: {devices: '1', max_batch_size: 5}
engine_args: {model_stage: talker, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: ar, scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler,
gpu_memory_utilization: 0.5, enforce_eager: false, trust_remote_code: true, engine_output_type: latent,
enable_prefix_caching: false, max_num_batched_tokens: 32768, max_model_len: 32768,
distributed_executor_backend: mp, hf_config_name: talker_config, load_format: dummy,
custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav_async_chunk}
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker
default_sampling_params:
temperature: 0.9
top_k: 50
max_tokens: 1000
seed: 42
detokenize: false
repetition_penalty: 1.05
stop_token_ids: [2150]
- stage_id: 2
runtime: {devices: '1', max_batch_size: 1}
engine_args: {model_stage: code2wav, model_arch: Qwen3OmniMoeForConditionalGeneration,
worker_type: generation, scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler,
enforce_eager: true, trust_remote_code: true, enable_prefix_caching: false, engine_output_type: audio,
gpu_memory_utilization: 0.1, distributed_executor_backend: mp, max_num_batched_tokens: 100000,
hf_config_name: thinker_config, async_scheduling: false, load_format: dummy}
engine_input_source: [1]
final_output: true
final_output_type: audio
default_sampling_params: {temperature: 0.0, top_p: 1.0, top_k: -1, max_tokens: 2000,
seed: 42, detokenize: true, repetition_penalty: 1.1}
async_chunk: true