diff --git a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs1.yaml b/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs1.yaml index ca441d286..c348e6714 100644 --- a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs1.yaml +++ b/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 diff --git a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs16.yaml b/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs16.yaml index 2cc5cf535..6c3fbdce6 100644 --- a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs16.yaml +++ b/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 diff --git a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs4.yaml b/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs4.yaml index 5de107d49..32f3f4dba 100644 --- a/benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs4.yaml +++ b/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 diff --git a/docs/configuration/pd_disaggregation.md b/docs/configuration/pd_disaggregation.md index 1cf6189e6..9d07ee18f 100644 --- a/docs/configuration/pd_disaggregation.md +++ b/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 diff --git a/docs/configuration/stage_configs.md b/docs/configuration/stage_configs.md index 95c42afcc..e3b6de848 100644 --- a/docs/configuration/stage_configs.md +++ b/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 ``` diff --git a/docs/configuration/stage_configs/qwen2_5_omni.yaml b/docs/configuration/stage_configs/qwen2_5_omni.yaml index 690577b84..2b3bd8e1c 100644 --- a/docs/configuration/stage_configs/qwen2_5_omni.yaml +++ b/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 diff --git a/docs/user_guide/examples/offline_inference/bagel.md b/docs/user_guide/examples/offline_inference/bagel.md index e62668687..1fb4d4045 100644 --- a/docs/user_guide/examples/offline_inference/bagel.md +++ b/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 diff --git a/examples/offline_inference/bagel/README.md b/examples/offline_inference/bagel/README.md index 48517b1cd..3e653d0e3 100644 --- a/examples/offline_inference/bagel/README.md +++ b/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 diff --git a/tests/dfx/perf/stage_configs/qwen3_tts.yaml b/tests/dfx/perf/stage_configs/qwen3_tts.yaml index 97b309056..7bf04deec 100644 --- a/tests/dfx/perf/stage_configs/qwen3_tts.yaml +++ b/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 diff --git a/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml b/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml index 1f0d06cb8..b7768c071 100644 --- a/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml +++ b/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 diff --git a/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml b/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml index 36b1d2bbe..504f3c98e 100644 --- a/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml +++ b/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 diff --git a/tests/e2e/offline_inference/stage_configs/npu/qwen2_5_omni_ci.yaml b/tests/e2e/offline_inference/stage_configs/npu/qwen2_5_omni_ci.yaml index f93a6c714..0a5513328 100644 --- a/tests/e2e/offline_inference/stage_configs/npu/qwen2_5_omni_ci.yaml +++ b/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 diff --git a/tests/e2e/stage_configs/dynin_omni_ci.yaml b/tests/e2e/stage_configs/dynin_omni_ci.yaml index 024000751..525b7d888 100644 --- a/tests/e2e/stage_configs/dynin_omni_ci.yaml +++ b/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 diff --git a/tests/e2e/stage_configs/qwen2_5_omni_ci.yaml b/tests/e2e/stage_configs/qwen2_5_omni_ci.yaml index a7c637d48..f6b0d3927 100644 --- a/tests/e2e/stage_configs/qwen2_5_omni_ci.yaml +++ b/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 diff --git a/tests/e2e/stage_configs/rocm/qwen2_5_omni_ci.yaml b/tests/e2e/stage_configs/rocm/qwen2_5_omni_ci.yaml index 0c756ce56..b33891fcc 100644 --- a/tests/e2e/stage_configs/rocm/qwen2_5_omni_ci.yaml +++ b/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 diff --git a/tests/e2e/stage_configs/xpu/qwen2_5_omni_ci.yaml b/tests/e2e/stage_configs/xpu/qwen2_5_omni_ci.yaml index 14ef3c343..8958eefaa 100644 --- a/tests/e2e/stage_configs/xpu/qwen2_5_omni_ci.yaml +++ b/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 diff --git a/vllm_omni/model_executor/models/qwen3_tts/pipeline.yaml b/vllm_omni/model_executor/models/qwen3_tts/pipeline.yaml index fd8ea3a3f..ec4c1c98b 100644 --- a/vllm_omni/model_executor/models/qwen3_tts/pipeline.yaml +++ b/vllm_omni/model_executor/models/qwen3_tts/pipeline.yaml @@ -90,4 +90,3 @@ connectors: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/bagel.yaml b/vllm_omni/model_executor/stage_configs/bagel.yaml index dfe9da1c2..75f7c8a06 100644 --- a/vllm_omni/model_executor/stage_configs/bagel.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/bagel_multiconnector.yaml b/vllm_omni/model_executor/stage_configs/bagel_multiconnector.yaml index af038f59f..7a0d851f0 100644 --- a/vllm_omni/model_executor/stage_configs/bagel_multiconnector.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/bagel_single_stage.yaml b/vllm_omni/model_executor/stage_configs/bagel_single_stage.yaml index bb24763f9..b2d4b07b1 100644 --- a/vllm_omni/model_executor/stage_configs/bagel_single_stage.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/bagel_think.yaml b/vllm_omni/model_executor/stage_configs/bagel_think.yaml index 0d2098a20..2575e6736 100644 --- a/vllm_omni/model_executor/stage_configs/bagel_think.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/bagel_usp2.yaml b/vllm_omni/model_executor/stage_configs/bagel_usp2.yaml index 33002b9aa..4599f8b05 100644 --- a/vllm_omni/model_executor/stage_configs/bagel_usp2.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/cosyvoice3_async_chunk.yaml b/vllm_omni/model_executor/stage_configs/cosyvoice3_async_chunk.yaml index ca7e9850a..13419ef10 100644 --- a/vllm_omni/model_executor/stage_configs/cosyvoice3_async_chunk.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/dynin_omni.yaml b/vllm_omni/model_executor/stage_configs/dynin_omni.yaml index 0724146aa..131a0d1cd 100644 --- a/vllm_omni/model_executor/stage_configs/dynin_omni.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/dynin_omni_multiconnector.yaml b/vllm_omni/model_executor/stage_configs/dynin_omni_multiconnector.yaml index 7259daa9e..4a54f8188 100644 --- a/vllm_omni/model_executor/stage_configs/dynin_omni_multiconnector.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml b/vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml index 0b0b27859..90f80c22d 100644 --- a/vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/glm_image.yaml b/vllm_omni/model_executor/stage_configs/glm_image.yaml index 3cc23e1e2..05ac84a7a 100644 --- a/vllm_omni/model_executor/stage_configs/glm_image.yaml +++ b/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 diff --git a/vllm_omni/model_executor/stage_configs/glm_image_muilticonnector.yaml b/vllm_omni/model_executor/stage_configs/glm_image_muilticonnector.yaml index 719c73a9f..7bd66c403 100644 --- a/vllm_omni/model_executor/stage_configs/glm_image_muilticonnector.yaml +++ b/vllm_omni/model_executor/stage_configs/glm_image_muilticonnector.yaml @@ -70,14 +70,9 @@ stage_args: # Top-level runtime config with MultiConnector support 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 to: 1 - window_size: -1 # OmniConnector configuration for efficient inter-stage tensor transfer connectors: diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_i2t.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_i2t.yaml index 203b54f25..b68b184ec 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_i2t.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_i2t.yaml @@ -39,6 +39,3 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_it2i.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_it2i.yaml index 9f6adece0..413e0f09c 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_it2i.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_it2i.yaml @@ -69,10 +69,6 @@ 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 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_moe_dit_2gpu_fp8.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_moe_dit_2gpu_fp8.yaml index aeef27a97..586b601bc 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_moe_dit_2gpu_fp8.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_moe_dit_2gpu_fp8.yaml @@ -30,6 +30,3 @@ stage_args: # Runtime edges runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i.yaml index a60fe9a5b..1d8c7f481 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i.yaml @@ -29,6 +29,3 @@ stage_args: # Runtime edges runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i_2gpu.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i_2gpu.yaml index e029c3836..41ed74ba6 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i_2gpu.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2i_2gpu.yaml @@ -39,6 +39,3 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2t.yaml b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2t.yaml index 60da8e0bc..a0a1a0dc1 100644 --- a/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2t.yaml +++ b/vllm_omni/model_executor/stage_configs/hunyuan_image3_t2t.yaml @@ -40,6 +40,3 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/model_executor/stage_configs/mimo_audio_async_chunk.yaml b/vllm_omni/model_executor/stage_configs/mimo_audio_async_chunk.yaml index b3c6bbbaf..2fa1b982a 100644 --- a/vllm_omni/model_executor/stage_configs/mimo_audio_async_chunk.yaml +++ b/vllm_omni/model_executor/stage_configs/mimo_audio_async_chunk.yaml @@ -74,10 +74,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 - connectors: connector_of_shared_memory: name: SharedMemoryConnector @@ -93,4 +89,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml b/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml index 0a307b447..9970765ef 100644 --- a/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml @@ -94,14 +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 diff --git a/vllm_omni/model_executor/stage_configs/qwen2_5_omni_multiconnector.yaml b/vllm_omni/model_executor/stage_configs/qwen2_5_omni_multiconnector.yaml index 6e4f871e3..6f5cc9959 100644 --- a/vllm_omni/model_executor/stage_configs/qwen2_5_omni_multiconnector.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen2_5_omni_multiconnector.yaml @@ -100,10 +100,6 @@ 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 - # Distributed connectors configuration (optional) # More connectors will be supported in the future. connectors: @@ -135,7 +131,5 @@ runtime: 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 diff --git a/vllm_omni/model_executor/stage_configs/qwen3_omni_moe_multiconnector.yaml b/vllm_omni/model_executor/stage_configs/qwen3_omni_moe_multiconnector.yaml index 6c2d2a766..5cb95d6a3 100644 --- a/vllm_omni/model_executor/stage_configs/qwen3_omni_moe_multiconnector.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen3_omni_moe_multiconnector.yaml @@ -111,10 +111,6 @@ stage_args: # Top-level runtime config: default windows and stage edges runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 - # Distributed connectors configuration connectors: # Mooncake connector for cross-node/intra-node communication @@ -137,7 +133,5 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 - from: 1 to: 2 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/qwen3_tts.yaml b/vllm_omni/model_executor/stage_configs/qwen3_tts.yaml index a0d38eb4b..80defdfea 100644 --- a/vllm_omni/model_executor/stage_configs/qwen3_tts.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen3_tts.yaml @@ -74,10 +74,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 - connectors: connector_of_shared_memory: name: SharedMemoryConnector @@ -96,4 +92,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml b/vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml index 75b2bab3a..d7ded0c51 100644 --- a/vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml @@ -75,10 +75,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 - connectors: connector_of_shared_memory: name: SharedMemoryConnector @@ -97,4 +93,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/qwen3_tts_uniproc.yaml b/vllm_omni/model_executor/stage_configs/qwen3_tts_uniproc.yaml index d2e920806..4ca8d11ad 100644 --- a/vllm_omni/model_executor/stage_configs/qwen3_tts_uniproc.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen3_tts_uniproc.yaml @@ -72,9 +72,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 connectors: connector_of_shared_memory: @@ -94,4 +91,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/voxcpm_async_chunk.yaml b/vllm_omni/model_executor/stage_configs/voxcpm_async_chunk.yaml index cf78d4e43..c6fd177a3 100644 --- a/vllm_omni/model_executor/stage_configs/voxcpm_async_chunk.yaml +++ b/vllm_omni/model_executor/stage_configs/voxcpm_async_chunk.yaml @@ -77,9 +77,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 connectors: voxcpm_shm: @@ -99,4 +96,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/model_executor/stage_configs/voxtral_tts.yaml b/vllm_omni/model_executor/stage_configs/voxtral_tts.yaml index 31cccb9cc..b0d9a81e7 100644 --- a/vllm_omni/model_executor/stage_configs/voxtral_tts.yaml +++ b/vllm_omni/model_executor/stage_configs/voxtral_tts.yaml @@ -82,10 +82,6 @@ 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 - connectors: connector_of_shared_memory: name: SharedMemoryConnector @@ -102,4 +98,3 @@ runtime: edges: - from: 0 # language_model → acoustic_transformer: trigger only after receiving full input (-1) to: 1 - window_size: -1 diff --git a/vllm_omni/platforms/npu/stage_configs/hunyuan_image3_t2i.yaml b/vllm_omni/platforms/npu/stage_configs/hunyuan_image3_t2i.yaml index 053e8a8cc..0fd03949d 100644 --- a/vllm_omni/platforms/npu/stage_configs/hunyuan_image3_t2i.yaml +++ b/vllm_omni/platforms/npu/stage_configs/hunyuan_image3_t2i.yaml @@ -33,6 +33,3 @@ stage_args: # Runtime defaults runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 diff --git a/vllm_omni/platforms/npu/stage_configs/qwen2_5_omni.yaml b/vllm_omni/platforms/npu/stage_configs/qwen2_5_omni.yaml index 8f7af161d..fe2fa45ed 100644 --- a/vllm_omni/platforms/npu/stage_configs/qwen2_5_omni.yaml +++ b/vllm_omni/platforms/npu/stage_configs/qwen2_5_omni.yaml @@ -85,13 +85,8 @@ 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 diff --git a/vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml b/vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml index cd82d91b7..586937d67 100644 --- a/vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml +++ b/vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml @@ -71,10 +71,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 - connectors: connector_of_shared_memory: name: SharedMemoryConnector @@ -93,4 +89,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/platforms/npu/stage_configs/voxcpm_async_chunk.yaml b/vllm_omni/platforms/npu/stage_configs/voxcpm_async_chunk.yaml index 0a4ed7497..87843634c 100644 --- a/vllm_omni/platforms/npu/stage_configs/voxcpm_async_chunk.yaml +++ b/vllm_omni/platforms/npu/stage_configs/voxcpm_async_chunk.yaml @@ -73,9 +73,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 connectors: connector_of_shared_memory: @@ -90,4 +87,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/platforms/rocm/stage_configs/qwen2_5_omni.yaml b/vllm_omni/platforms/rocm/stage_configs/qwen2_5_omni.yaml index 35e819354..c0860eac7 100644 --- a/vllm_omni/platforms/rocm/stage_configs/qwen2_5_omni.yaml +++ b/vllm_omni/platforms/rocm/stage_configs/qwen2_5_omni.yaml @@ -89,14 +89,8 @@ 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 diff --git a/vllm_omni/platforms/xpu/stage_configs/bagel.yaml b/vllm_omni/platforms/xpu/stage_configs/bagel.yaml index 0fc8a25ea..7b27f6a44 100644 --- a/vllm_omni/platforms/xpu/stage_configs/bagel.yaml +++ b/vllm_omni/platforms/xpu/stage_configs/bagel.yaml @@ -67,10 +67,6 @@ 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: @@ -83,4 +79,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1 diff --git a/vllm_omni/platforms/xpu/stage_configs/hunyuan_image3_t2i.yaml b/vllm_omni/platforms/xpu/stage_configs/hunyuan_image3_t2i.yaml index 8f969ced5..4e0005f82 100644 --- a/vllm_omni/platforms/xpu/stage_configs/hunyuan_image3_t2i.yaml +++ b/vllm_omni/platforms/xpu/stage_configs/hunyuan_image3_t2i.yaml @@ -78,6 +78,3 @@ 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 diff --git a/vllm_omni/platforms/xpu/stage_configs/qwen2_5_omni.yaml b/vllm_omni/platforms/xpu/stage_configs/qwen2_5_omni.yaml index 7dbedb29a..56306e364 100644 --- a/vllm_omni/platforms/xpu/stage_configs/qwen2_5_omni.yaml +++ b/vllm_omni/platforms/xpu/stage_configs/qwen2_5_omni.yaml @@ -88,14 +88,8 @@ 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 diff --git a/vllm_omni/platforms/xpu/stage_configs/voxtral_tts.yaml b/vllm_omni/platforms/xpu/stage_configs/voxtral_tts.yaml index 10051c1ed..0820ab632 100644 --- a/vllm_omni/platforms/xpu/stage_configs/voxtral_tts.yaml +++ b/vllm_omni/platforms/xpu/stage_configs/voxtral_tts.yaml @@ -88,9 +88,6 @@ stage_args: runtime: enabled: true - defaults: - window_size: -1 - max_inflight: 1 connectors: connector_of_shared_memory: @@ -108,4 +105,3 @@ runtime: edges: - from: 0 to: 1 - window_size: -1