[Cleanup] Remove dead runtime.defaults config parameters

benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs1.yaml

@@ -71,10 +71,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
-
   connectors:
     connector_of_shared_memory:
       name: SharedMemoryConnector
@@ -90,4 +86,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs16.yaml

@@ -72,10 +72,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 16
-
   connectors:
     connector_of_shared_memory:
       name: SharedMemoryConnector
@@ -91,4 +87,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs4.yaml

@@ -72,10 +72,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 4
-
   connectors:
     connector_of_shared_memory:
       name: SharedMemoryConnector
@@ -91,4 +87,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

docs/configuration/pd_disaggregation.md

@@ -145,19 +145,13 @@ Compared with the default Qwen3-Omni config:
 ```yaml
 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
     - from: 2
       to: 3
-      window_size: -1
 ```
 
 ## 4. Launch with your custom config

docs/configuration/stage_configs.md

@@ -114,16 +114,12 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
+
   edges:
     - from: 0                   # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1                   # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1
 
 ```
 

docs/configuration/stage_configs/qwen2_5_omni.yaml

@@ -82,13 +82,8 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
   edges:
     - from: 0                   # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1                   # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1

docs/user_guide/examples/offline_inference/bagel.md

@@ -176,8 +176,6 @@ Example configuration for TP=2 on GPUs 0 and 1:
 
 | Parameter             | Value   | Description                      |
 | :-------------------- | :------ | :------------------------------- |
-| `window_size`         | `-1`    | Window size (-1 means unlimited) |
-| `max_inflight`        | `1`     | Maximum inflight requests        |
 | `shm_threshold_bytes` | `65536` | Shared memory threshold (64KB)   |
 
 ## Using Mooncake Connector

examples/offline_inference/bagel/README.md

@@ -173,8 +173,6 @@ Example configuration for TP=2 on GPUs 0 and 1:
 
 | Parameter             | Value   | Description                      |
 | :-------------------- | :------ | :------------------------------- |
-| `window_size`         | `-1`    | Window size (-1 means unlimited) |
-| `max_inflight`        | `1`     | Maximum inflight requests        |
 | `shm_threshold_bytes` | `65536` | Shared memory threshold (64KB)   |
 
 ## Using Mooncake Connector

tests/dfx/perf/stage_configs/qwen3_tts.yaml

@@ -74,10 +74,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 4
-
   connectors:
     connector_of_shared_memory:
       name: SharedMemoryConnector
@@ -93,4 +89,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml

@@ -64,9 +64,6 @@ stage_args:
 # Top-level runtime config with Mooncake connector
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
   connectors:
     mooncake_connector:
       name: MooncakeConnector
@@ -80,4 +77,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml

@@ -62,10 +62,6 @@ stage_args:
 # Runtime edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
-
   # Distributed connectors configuration (optional)
   # More connectors will be supported in the future.
   connectors:
@@ -78,4 +74,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

tests/e2e/offline_inference/stage_configs/npu/qwen2_5_omni_ci.yaml

@@ -91,13 +91,8 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
   edges:
     - from: 0                   # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1                   # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1

tests/e2e/stage_configs/dynin_omni_ci.yaml

@@ -72,13 +72,8 @@ stage_args:
 
 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.yaml

@@ -97,13 +97,8 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
   edges:
     - from: 0                   # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1                   # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1

tests/e2e/stage_configs/rocm/qwen2_5_omni_ci.yaml

@@ -94,13 +94,8 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
   edges:
     - from: 0                   # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1                   # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1

tests/e2e/stage_configs/xpu/qwen2_5_omni_ci.yaml

@@ -95,14 +95,8 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1 # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1 # Simplified: process serially within each stage
-
   edges:
     - from: 0 # thinker → talker: trigger only after receiving full input (-1)
       to: 1
-      window_size: -1
     - from: 1 # talker → code2wav: trigger only after receiving full input (-1)
       to: 2
-      window_size: -1

vllm_omni/model_executor/models/qwen3_tts/pipeline.yaml

@@ -90,4 +90,3 @@ connectors:
 edges:
   - from: 0
     to: 1
-    window_size: -1

vllm_omni/model_executor/stage_configs/bagel.yaml

@@ -71,10 +71,6 @@ stage_args:
 # Runtime edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
-
   # Distributed connectors configuration (optional)
   # More connectors will be supported in the future.
   connectors:
@@ -104,4 +100,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/bagel_multiconnector.yaml

@@ -64,10 +64,6 @@ stage_args:
 # Runtime edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
-
   # Distributed connectors configuration (optional)
   # More connectors will be supported in the future.
   connectors:
@@ -104,4 +100,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/bagel_single_stage.yaml

@@ -22,6 +22,3 @@ stage_args:
 # Runtime edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1

vllm_omni/model_executor/stage_configs/bagel_think.yaml

@@ -65,9 +65,6 @@ stage_args:
 # Runtime edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
 
   connectors:
     shared_memory_connector:
@@ -78,4 +75,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/bagel_usp2.yaml

@@ -62,9 +62,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
   connectors:
     shared_memory_connector:
       name: SharedMemoryConnector
@@ -73,4 +70,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/cosyvoice3_async_chunk.yaml

@@ -63,9 +63,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 1
 
   connectors:
     connector_of_shared_memory:
@@ -82,4 +79,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/dynin_omni.yaml

@@ -67,14 +67,9 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
 
   edges:
     - from: 0
       to: 1
-      window_size: -1
     - from: 1
       to: 2
-      window_size: -1

vllm_omni/model_executor/stage_configs/dynin_omni_multiconnector.yaml

@@ -71,9 +71,6 @@ stage_args:
 # Top-level runtime config (concise): default windows and stage edges
 runtime:
   enabled: true
-  defaults:
-    window_size: -1             # Simplified: trigger downstream only after full upstream completion
-    max_inflight: 1             # Simplified: process serially within each stage
   ####
   # same as Qwen2.5_omni version
   # Distributed connectors configuration (optional)
@@ -108,7 +105,5 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1
     - from: 1
       to: 2
-      window_size: -1

vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml

@@ -71,10 +71,6 @@ stage_args:
 
 runtime:
   enabled: true
-  defaults:
-    window_size: -1
-    max_inflight: 16
-
   connectors:
     connector_of_shared_memory:
       name: SharedMemoryConnector
@@ -93,4 +89,3 @@ runtime:
   edges:
     - from: 0
       to: 1
-      window_size: -1

vllm_omni/model_executor/stage_configs/glm_image.yaml

@@ -70,11 +70,6 @@ stage_args:
 # Top-level runtime config
 runtime:
   enabled: true
-  defaults:
-    window_size: -1 # Trigger downstream only after full upstream completion
-    max_inflight: 1 # Process serially within each stage
-
   edges:
     - from: 0 # AR → Diffusion: trigger after AR completes
       to: 1
-      window_size: -1