diff --git a/vllm/model_executor/models/qwen2_5_omni_thinker.py b/vllm/model_executor/models/qwen2_5_omni_thinker.py index 7ce7dc8319..14f4c424bb 100644 --- a/vllm/model_executor/models/qwen2_5_omni_thinker.py +++ b/vllm/model_executor/models/qwen2_5_omni_thinker.py @@ -952,8 +952,6 @@ class Qwen2_5OmniConditionalGenerationMixin: def _process_audio_input( self, audio_input: Qwen2_5OmniAudioFeatureInputs, - audio_hashes: list[str] | None = None, - cached_audio_features: torch.Tensor | None = None, ) -> torch.Tensor: input_features = audio_input["input_features"] audio_feature_lengths = audio_input["audio_feature_lengths"] @@ -990,8 +988,6 @@ class Qwen2_5OmniConditionalGenerationMixin: def _process_video_input( self, video_input: Qwen2_5_VLVideoInputs, - video_hashes: list[str] = None, - cached_video_embeds: torch.Tensor = None, ) -> torch.Tensor: if video_input["type"] == "video_embeds": return video_input["video_embeds"].type(self.visual.dtype) diff --git a/vllm/model_executor/models/qwen3_asr.py b/vllm/model_executor/models/qwen3_asr.py index 1d8e1bbaa4..37903462dd 100644 --- a/vllm/model_executor/models/qwen3_asr.py +++ b/vllm/model_executor/models/qwen3_asr.py @@ -363,8 +363,6 @@ class Qwen3ASRForConditionalGeneration( def _process_audio_input( self, audio_input: Qwen2_5OmniAudioFeatureInputs, - audio_hashes: list[str] | None = None, - cached_audio_features: torch.Tensor | None = None, ) -> torch.Tensor: input_features = audio_input["input_features"] audio_feature_lengths = audio_input["audio_feature_lengths"] diff --git a/vllm/model_executor/models/qwen3_omni_moe_thinker.py b/vllm/model_executor/models/qwen3_omni_moe_thinker.py index 8cee51a126..b4842e0638 100755 --- a/vllm/model_executor/models/qwen3_omni_moe_thinker.py +++ b/vllm/model_executor/models/qwen3_omni_moe_thinker.py @@ -1646,8 +1646,6 @@ class Qwen3OmniMoeConditionalGenerationMixin(Qwen2_5OmniConditionalGenerationMix def _process_audio_input( self, audio_input: Qwen2_5OmniAudioFeatureInputs, - audio_hashes: list[str] | None = None, - cached_audio_features: torch.Tensor | None = None, ) -> tuple[torch.Tensor, ...]: input_features = audio_input["input_features"] audio_feature_lengths = audio_input["audio_feature_lengths"] diff --git a/vllm/v1/engine/async_llm.py b/vllm/v1/engine/async_llm.py index 1c87d9ec09..45ae416529 100644 --- a/vllm/v1/engine/async_llm.py +++ b/vllm/v1/engine/async_llm.py @@ -77,7 +77,6 @@ class AsyncLLM(EngineClient): log_stats: bool, usage_context: UsageContext = UsageContext.ENGINE_CONTEXT, mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY, - use_cached_outputs: bool = False, log_requests: bool = True, start_engine_loop: bool = True, stat_loggers: list[StatLoggerFactory] | None = None, @@ -95,7 +94,6 @@ class AsyncLLM(EngineClient): log_stats: Whether to log stats. usage_context: Usage context of the LLM. mm_registry: Multi-modal registry. - use_cached_outputs: Whether to use cached outputs. log_requests: Whether to log requests. start_engine_loop: Whether to start the engine loop. stat_loggers: customized stat loggers for the engine. diff --git a/vllm/v1/engine/llm_engine.py b/vllm/v1/engine/llm_engine.py index d0545651b9..62c7d0e2a8 100644 --- a/vllm/v1/engine/llm_engine.py +++ b/vllm/v1/engine/llm_engine.py @@ -56,7 +56,6 @@ class LLMEngine: usage_context: UsageContext = UsageContext.ENGINE_CONTEXT, stat_loggers: list[StatLoggerFactory] | None = None, mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY, - use_cached_outputs: bool = False, multiprocess_mode: bool = False, ) -> None: self.vllm_config = vllm_config