[Bugfix] Remove duplicated config keyword max batch size (#1851)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
This commit is contained in:
1 parent
4c2293743b
commit
05d8de813e
67 files changed
+226
-159
No files matched your search
@@ -7,9 +7,9 @@ stage_args:
|
||||
prompt_expand_func: vllm_omni.model_executor.stage_input_processors.bagel.expand_cfg_prompts
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
max_num_seqs: 1
|
||||
model_arch: BagelForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -44,9 +44,9 @@ stage_args:
|
||||
cfg_kv_collect_func: vllm_omni.model_executor.stage_input_processors.bagel.collect_cfg_kv_caches
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: dit
|
||||
max_num_seqs: 1
|
||||
gpu_memory_utilization: 0.45
|
||||
enforce_eager: true
|
||||
trust_remote_code: true
|
||||
|
||||
@@ -7,9 +7,9 @@ stage_args:
|
||||
prompt_expand_func: vllm_omni.model_executor.stage_input_processors.bagel.expand_cfg_prompts
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
max_num_seqs: 1
|
||||
model_arch: OmniBagelForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -43,9 +43,9 @@ stage_args:
|
||||
cfg_kv_collect_func: vllm_omni.model_executor.stage_input_processors.bagel.collect_cfg_kv_caches
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: dit
|
||||
max_num_seqs: 1
|
||||
gpu_memory_utilization: 0.45
|
||||
enforce_eager: true
|
||||
trust_remote_code: true
|
||||
|
||||
@@ -6,7 +6,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true # Run this stage in a separate process
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -37,7 +36,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: talker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -67,9 +65,9 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "0" # Example: use a different GPU than the previous stage; use "0" if single GPU
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: code2wav
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: generation
|
||||
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
||||
|
||||
@@ -7,7 +7,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true # Run this stage in a separate process
|
||||
devices: "0" # Visible devices for this stage (CUDA_VISIBLE_DEVICES/torch.cuda.set_device)
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -38,7 +37,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: talker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -68,9 +66,9 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "2" # Example: use a different GPU than the previous stage; use "0" if single GPU
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: code2wav
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: generation
|
||||
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
||||
|
||||
@@ -3,7 +3,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true # Run this stage in a separate process
|
||||
devices: "0" # Visible devices for this stage (CUDA_VISIBLE_DEVICES/torch.cuda.set_device)
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
|
||||
@@ -8,9 +8,9 @@ stage_args:
|
||||
- stage_id: 0
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 5
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
max_num_seqs: 5
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -42,9 +42,9 @@ stage_args:
|
||||
- stage_id: 1
|
||||
runtime:
|
||||
devices: "1"
|
||||
max_batch_size: 5
|
||||
engine_args:
|
||||
model_stage: talker
|
||||
max_num_seqs: 5
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -72,9 +72,9 @@ stage_args:
|
||||
- stage_id: 2
|
||||
runtime:
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: code2wav
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: generation
|
||||
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
||||
|
||||
@@ -7,7 +7,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true # Run this stage in a separate process
|
||||
devices: "0" # Visible devices for this stage (CUDA_VISIBLE_DEVICES/torch.cuda.set_device)
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -38,7 +37,6 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: talker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
@@ -68,9 +66,9 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "0" # Example: use a different GPU than the previous stage; use "0" if single GPU
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: code2wav
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: generation
|
||||
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
||||
|
||||
@@ -8,9 +8,9 @@ stage_args:
|
||||
- stage_id: 0
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: thinker
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -39,9 +39,9 @@ stage_args:
|
||||
- stage_id: 1
|
||||
runtime:
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: talker
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
||||
@@ -70,9 +70,9 @@ stage_args:
|
||||
- stage_id: 2
|
||||
runtime:
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
model_stage: code2wav
|
||||
max_num_seqs: 1
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: generation
|
||||
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
||||
|
||||
@@ -7,8 +7,8 @@ stage_args:
|
||||
runtime:
|
||||
process: true # Run this stage in a separate process
|
||||
devices: "0" # Visible devices for this stage
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: thinker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -39,8 +39,8 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "1"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: talker
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -71,8 +71,8 @@ stage_args:
|
||||
runtime:
|
||||
process: true
|
||||
devices: "2"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: code2wav
|
||||
model_arch: Qwen2_5OmniForConditionalGeneration
|
||||
worker_type: generation
|
||||
|
||||
@@ -9,8 +9,8 @@ stage_args:
|
||||
stage_type: llm # Use llm stage type for AR stages
|
||||
runtime:
|
||||
devices: "0,1,2,3"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: thinker
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -44,8 +44,8 @@ stage_args:
|
||||
stage_type: llm # Use llm stage type for AR stages
|
||||
runtime:
|
||||
devices: "4"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: talker
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -78,8 +78,8 @@ stage_args:
|
||||
stage_type: llm # Use llm stage type for AR stages
|
||||
runtime:
|
||||
devices: "5"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
model_stage: code2wav
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: generation
|
||||
|
||||
Reference in new issue
Block a user