[Docs] optimize and supplement docs system (#86)
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
This commit is contained in:
Gao Han authored and GitHub committed
1 parent
38f58064eb
commit
db81ee9f69
75 files changed
+2452
-512
No files matched your search
@@ -0,0 +1,88 @@
|
||||
# Summary
|
||||
|
||||
## Entry Points
|
||||
|
||||
Main entry points for vLLM-omni inference and serving.
|
||||
|
||||
- [vllm_omni.entrypoints.async_omni_llm.AsyncOmniLLM][]
|
||||
- [vllm_omni.entrypoints.async_omni_llm.AsyncOmniStageLLM][]
|
||||
- [vllm_omni.entrypoints.chat_utils.OmniAsyncMultiModalContentParser][]
|
||||
- [vllm_omni.entrypoints.chat_utils.OmniAsyncMultiModalItemTracker][]
|
||||
- [vllm_omni.entrypoints.chat_utils.parse_chat_messages_futures][]
|
||||
- [vllm_omni.entrypoints.cli.serve.OmniServeCommand][]
|
||||
- [vllm_omni.entrypoints.log_utils.OrchestratorMetrics][]
|
||||
- [vllm_omni.entrypoints.omni_llm.OmniLLM][]
|
||||
- [vllm_omni.entrypoints.omni_llm.OmniStageLLM][]
|
||||
- [vllm_omni.entrypoints.omni_stage.OmniStage][]
|
||||
- [vllm_omni.entrypoints.openai.serving_chat.OmniOpenAIServingChat][]
|
||||
|
||||
## Inputs
|
||||
|
||||
Input data structures for multi-modal inputs.
|
||||
|
||||
- [vllm_omni.inputs.data.OmniEmbedsPrompt][]
|
||||
- [vllm_omni.inputs.data.OmniTokenInputs][]
|
||||
- [vllm_omni.inputs.data.OmniTokensPrompt][]
|
||||
- [vllm_omni.inputs.parse.parse_singleton_prompt_omni][]
|
||||
- [vllm_omni.inputs.preprocess.OmniInputPreprocessor][]
|
||||
|
||||
## Engine
|
||||
|
||||
Engine classes for offline and online inference.
|
||||
|
||||
- [vllm_omni.engine.AdditionalInformationEntry][]
|
||||
- [vllm_omni.engine.AdditionalInformationPayload][]
|
||||
- [vllm_omni.engine.OmniEngineCoreRequest][]
|
||||
- [vllm_omni.engine.PromptEmbedsPayload][]
|
||||
- [vllm_omni.engine.arg_utils.AsyncOmniEngineArgs][]
|
||||
- [vllm_omni.engine.arg_utils.OmniEngineArgs][]
|
||||
- [vllm_omni.engine.output_processor.MultimodalOutputProcessor][]
|
||||
- [vllm_omni.engine.output_processor.OmniRequestState][]
|
||||
- [vllm_omni.engine.processor.OmniProcessor][]
|
||||
|
||||
## Core
|
||||
|
||||
Core scheduling and caching components.
|
||||
|
||||
- [vllm_omni.core.dit_cache_manager.DiTCacheManager][]
|
||||
- [vllm_omni.core.sched.diffusion_scheduler.DiffusionScheduler][]
|
||||
- [vllm_omni.core.sched.output.OmniNewRequestData][]
|
||||
- [vllm_omni.core.sched.scheduler.OmniScheduler][]
|
||||
|
||||
## Model Executor
|
||||
|
||||
Model execution components.
|
||||
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni.OmniOutput][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni.Qwen2_5OmniForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_talker.Qwen2_5OmniTalkerForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniAudioFeatureInputs][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniConditionalGenerationMixin][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerDummyInputsBuilder][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerMultiModalDataParser][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerMultiModalProcessor][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerProcessingInfo][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavBigVGANModel][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavDiTModel][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavForConditionalGenerationVLLM][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavModel][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_old.Qwen2EmbeddingModel][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_old.Qwen2ForCausalLM][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_old.Qwen2Model][]
|
||||
|
||||
## Configuration
|
||||
|
||||
Configuration classes.
|
||||
|
||||
- [vllm_omni.config.model.OmniModelConfig][]
|
||||
|
||||
## Workers
|
||||
|
||||
Worker classes and model runners for distributed inference.
|
||||
|
||||
- [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][]
|
||||
- [vllm_omni.worker.gpu_ar_worker.GPUARWorker][]
|
||||
- [vllm_omni.worker.gpu_diffusion_model_runner.GPUDiffusionModelRunner][]
|
||||
- [vllm_omni.worker.gpu_diffusion_worker.GPUDiffusionWorker][]
|
||||
- [vllm_omni.worker.gpu_model_runner.OmniGPUModelRunner][]
|
||||
@@ -1,68 +0,0 @@
|
||||
# Summary
|
||||
|
||||
## Entry Points
|
||||
|
||||
Main entry points for vLLM-omni inference and serving.
|
||||
|
||||
- [vllm_omni.entrypoints.omni_llm.OmniLLM][]
|
||||
- [vllm_omni.entrypoints.omni_llm.OmniStageLLM][]
|
||||
- [vllm_omni.entrypoints.omni_stage.OmniStage][]
|
||||
- [vllm_omni.entrypoints.cli.serve.OmniServeCommand][]
|
||||
|
||||
## Inputs
|
||||
|
||||
Input data structures for multi-modal inputs.
|
||||
|
||||
- [vllm_omni.inputs.data.OmniTokenInputs][]
|
||||
- [vllm_omni.inputs.data.OmniTokensPrompt][]
|
||||
- [vllm_omni.inputs.data.OmniEmbedsPrompt][]
|
||||
- [vllm_omni.inputs.parse.parse_singleton_prompt_omni][]
|
||||
- [vllm_omni.inputs.preprocess.OmniInputPreprocessor][]
|
||||
|
||||
## Engine
|
||||
|
||||
Engine classes for offline and online inference.
|
||||
|
||||
- [vllm_omni.engine.arg_utils.OmniEngineArgs][]
|
||||
- [vllm_omni.engine.processor.OmniProcessor][]
|
||||
- [vllm_omni.engine.output_processor.OmniRequestState][]
|
||||
- [vllm_omni.engine.output_processor.MultimodalOutputProcessor][]
|
||||
- [vllm_omni.engine.PromptEmbedsPayload][]
|
||||
- [vllm_omni.engine.AdditionalInformationPayload][]
|
||||
- [vllm_omni.engine.OmniEngineCoreRequest][]
|
||||
|
||||
## Core
|
||||
|
||||
Core scheduling and caching components.
|
||||
|
||||
- [vllm_omni.core.sched.scheduler.OmniScheduler][]
|
||||
- [vllm_omni.core.sched.diffusion_scheduler.DiffusionScheduler][]
|
||||
- [vllm_omni.core.sched.output.OmniNewRequestData][]
|
||||
- [vllm_omni.core.dit_cache_manager.DiTCacheManager][]
|
||||
|
||||
## Model Executor
|
||||
|
||||
Model execution components.
|
||||
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni.Qwen2_5OmniForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni_talker.Qwen2_5OmniTalkerForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni_thinker.Qwen2_5OmniThinkerForConditionalGeneration][]
|
||||
- [vllm_omni.model_executor.models.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavForConditionalGenerationVLLM][]
|
||||
- [vllm_omni.model_executor.layers.mrope.MRotaryEmbedding][]
|
||||
- [vllm_omni.model_executor.models.registry.OmniModelRegistry][]
|
||||
|
||||
## Configuration
|
||||
|
||||
Configuration classes.
|
||||
|
||||
- [vllm_omni.config.OmniModelConfig][]
|
||||
|
||||
## Workers
|
||||
|
||||
Worker classes and model runners for distributed inference.
|
||||
|
||||
- [vllm_omni.worker.gpu_ar_worker.GPUARWorker][]
|
||||
- [vllm_omni.worker.gpu_diffusion_worker.GPUDiffusionWorker][]
|
||||
- [vllm_omni.worker.gpu_model_runner.OmniGPUModelRunner][]
|
||||
- [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][]
|
||||
- [vllm_omni.worker.gpu_diffusion_model_runner.GPUDiffusionModelRunner][]
|
||||
Reference in new issue
Block a user