[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
@@ -32,8 +32,8 @@ stage_args:
|
||||
is_prefill_only: true
|
||||
runtime:
|
||||
devices: "0"
|
||||
max_batch_size: 16
|
||||
engine_args:
|
||||
max_num_seqs: 16
|
||||
model_stage: thinker
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -70,8 +70,8 @@ stage_args:
|
||||
is_decode_only: true
|
||||
runtime:
|
||||
devices: "1"
|
||||
max_batch_size: 64
|
||||
engine_args:
|
||||
max_num_seqs: 64
|
||||
model_stage: thinker
|
||||
model_arch: Qwen3OmniMoeForConditionalGeneration
|
||||
worker_type: ar
|
||||
@@ -128,7 +128,8 @@ After inserting the extra thinker stage, renumber the remaining stages:
|
||||
- stage_id: 3
|
||||
runtime:
|
||||
devices: "2"
|
||||
max_batch_size: 1
|
||||
engine_args:
|
||||
max_num_seqs: 1
|
||||
engine_input_source: [2]
|
||||
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav
|
||||
```
|
||||
|
||||
Reference in new issue
Block a user