Add full API docs and improve the UX of navigating them (#17485)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

docs/source/api/engine/async_llm_engine.md

@@ -1,7 +0,0 @@
-# AsyncLLMEngine
-
-```{eval-rst}
-.. autoclass:: vllm.AsyncLLMEngine
-    :members:
-    :show-inheritance:
-```

docs/source/api/engine/index.md

@@ -1,17 +0,0 @@
-# vLLM Engine
-
-```{eval-rst}
-.. automodule:: vllm.engine
-```
-
-```{eval-rst}
-.. currentmodule:: vllm.engine
-```
-
-:::{toctree}
-:caption: Engines
-:maxdepth: 2
-
-llm_engine
-async_llm_engine
-:::

docs/source/api/engine/llm_engine.md

@@ -1,7 +0,0 @@
-# LLMEngine
-
-```{eval-rst}
-.. autoclass:: vllm.LLMEngine
-    :members:
-    :show-inheritance:
-```

docs/source/api/inference_params.md

@@ -1,21 +0,0 @@
-# Inference Parameters
-
-Inference parameters for vLLM APIs.
-
-(sampling-params)=
-
-## Sampling Parameters
-
-```{eval-rst}
-.. autoclass:: vllm.SamplingParams
-    :members:
-```
-
-(pooling-params)=
-
-## Pooling Parameters
-
-```{eval-rst}
-.. autoclass:: vllm.PoolingParams
-    :members:
-```

docs/source/api/model/adapters.md

@@ -1,9 +0,0 @@
-# Model Adapters
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.model_executor.models.adapters
-    :members:
-    :member-order: bysource
-```

docs/source/api/model/index.md

@@ -1,11 +0,0 @@
-# Model Development
-
-## Submodules
-
-:::{toctree}
-:maxdepth: 1
-
-interfaces_base
-interfaces
-adapters
-:::

docs/source/api/model/interfaces.md

@@ -1,9 +0,0 @@
-# Optional Interfaces
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.model_executor.models.interfaces
-    :members:
-    :member-order: bysource
-```

docs/source/api/model/interfaces_base.md

@@ -1,9 +0,0 @@
-# Base Model Interfaces
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.model_executor.models.interfaces_base
-    :members:
-    :member-order: bysource
-```

docs/source/api/multimodal/index.md

@@ -1,28 +0,0 @@
-(multi-modality)=
-
-# Multi-Modality
-
-vLLM provides experimental support for multi-modal models through the {mod}`vllm.multimodal` package.
-
-Multi-modal inputs can be passed alongside text and token prompts to [supported models](#supported-mm-models)
-via the `multi_modal_data` field in {class}`vllm.inputs.PromptType`.
-
-Looking to add your own multi-modal model? Please follow the instructions listed [here](#supports-multimodal).
-
-## Module Contents
-
-```{eval-rst}
-.. autodata:: vllm.multimodal.MULTIMODAL_REGISTRY
-```
-
-## Submodules
-
-:::{toctree}
-:maxdepth: 1
-
-inputs
-parse
-processing
-profiling
-registry
-:::

docs/source/api/multimodal/inputs.md

@@ -1,49 +0,0 @@
-# Input Definitions
-
-## User-facing inputs
-
-```{eval-rst}
-.. autodata:: vllm.multimodal.inputs.MultiModalDataDict
-```
-
-## Internal data structures
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.PlaceholderRange
-    :members:
-    :show-inheritance:
-```
-
-```{eval-rst}
-.. autodata:: vllm.multimodal.inputs.NestedTensors
-```
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.MultiModalFieldElem
-    :members:
-    :show-inheritance:
-```
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.MultiModalFieldConfig
-    :members:
-    :show-inheritance:
-```
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.MultiModalKwargsItem
-    :members:
-    :show-inheritance:
-```
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.MultiModalKwargs
-    :members:
-    :show-inheritance:
-```
-
-```{eval-rst}
-.. autoclass:: vllm.multimodal.inputs.MultiModalInputs
-    :members:
-    :show-inheritance:
-```

docs/source/api/multimodal/parse.md

@@ -1,9 +0,0 @@
-# Data Parsing
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.multimodal.parse
-    :members:
-    :member-order: bysource
-```

docs/source/api/multimodal/processing.md

@@ -1,9 +0,0 @@
-# Data Processing
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.multimodal.processing
-    :members:
-    :member-order: bysource
-```

docs/source/api/multimodal/profiling.md

@@ -1,9 +0,0 @@
-# Memory Profiling
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.multimodal.profiling
-    :members:
-    :member-order: bysource
-```

docs/source/api/multimodal/registry.md

@@ -1,9 +0,0 @@
-# Registry
-
-## Module Contents
-
-```{eval-rst}
-.. automodule:: vllm.multimodal.registry
-    :members:
-    :member-order: bysource
-```

docs/source/api/offline_inference/index.md

@@ -1,9 +0,0 @@
-# Offline Inference
-
-:::{toctree}
-:caption: Contents
-:maxdepth: 1
-
-llm
-llm_inputs
-:::

docs/source/api/offline_inference/llm.md

@@ -1,7 +0,0 @@
-# LLM Class
-
-```{eval-rst}
-.. autoclass:: vllm.LLM
-    :members:
-    :show-inheritance:
-```

docs/source/api/offline_inference/llm_inputs.md

@@ -1,19 +0,0 @@
-# LLM Inputs
-
-```{eval-rst}
-.. autodata:: vllm.inputs.PromptType
-```
-
-```{eval-rst}
-.. autoclass:: vllm.inputs.TextPrompt
-    :show-inheritance:
-    :members:
-    :member-order: bysource
-```
-
-```{eval-rst}
-.. autoclass:: vllm.inputs.TokensPrompt
-    :show-inheritance:
-    :members:
-    :member-order: bysource
-```

docs/source/api/summary.md

@@ -0,0 +1,133 @@
+# Summary
+
+(configuration)=
+
+## Configuration
+
+API documentation for vLLM's configuration classes.
+
+```{autodoc2-summary}
+    vllm.config.ModelConfig
+    vllm.config.CacheConfig
+    vllm.config.TokenizerPoolConfig
+    vllm.config.LoadConfig
+    vllm.config.ParallelConfig
+    vllm.config.SchedulerConfig
+    vllm.config.DeviceConfig
+    vllm.config.SpeculativeConfig
+    vllm.config.LoRAConfig
+    vllm.config.PromptAdapterConfig
+    vllm.config.MultiModalConfig
+    vllm.config.PoolerConfig
+    vllm.config.DecodingConfig
+    vllm.config.ObservabilityConfig
+    vllm.config.KVTransferConfig
+    vllm.config.CompilationConfig
+    vllm.config.VllmConfig
+```
+
+(offline-inference-api)=
+
+## Offline Inference
+
+LLM Class.
+
+```{autodoc2-summary}
+    vllm.LLM
+```
+
+LLM Inputs.
+
+```{autodoc2-summary}
+    vllm.inputs.PromptType
+    vllm.inputs.TextPrompt
+    vllm.inputs.TokensPrompt
+```
+
+## vLLM Engines
+
+Engine classes for offline and online inference.
+
+```{autodoc2-summary}
+    vllm.LLMEngine
+    vllm.AsyncLLMEngine
+```
+
+## Inference Parameters
+
+Inference parameters for vLLM APIs.
+
+(sampling-params)=
+(pooling-params)=
+
+```{autodoc2-summary}
+    vllm.SamplingParams
+    vllm.PoolingParams
+```
+
+(multi-modality)=
+
+## Multi-Modality
+
+vLLM provides experimental support for multi-modal models through the {mod}`vllm.multimodal` package.
+
+Multi-modal inputs can be passed alongside text and token prompts to [supported models](#supported-mm-models)
+via the `multi_modal_data` field in {class}`vllm.inputs.PromptType`.
+
+Looking to add your own multi-modal model? Please follow the instructions listed [here](#supports-multimodal).
+
+```{autodoc2-summary}
+    vllm.multimodal.MULTIMODAL_REGISTRY
+```
+
+### Inputs
+
+User-facing inputs.
+
+```{autodoc2-summary}
+    vllm.multimodal.inputs.MultiModalDataDict
+```
+
+Internal data structures.
+
+```{autodoc2-summary}
+    vllm.multimodal.inputs.PlaceholderRange
+    vllm.multimodal.inputs.NestedTensors
+    vllm.multimodal.inputs.MultiModalFieldElem
+    vllm.multimodal.inputs.MultiModalFieldConfig
+    vllm.multimodal.inputs.MultiModalKwargsItem
+    vllm.multimodal.inputs.MultiModalKwargs
+    vllm.multimodal.inputs.MultiModalInputs
+```
+
+### Data Parsing
+
+```{autodoc2-summary}
+    vllm.multimodal.parse
+```
+
+### Data Processing
+
+```{autodoc2-summary}
+    vllm.multimodal.processing
+```
+
+### Memory Profiling
+
+```{autodoc2-summary}
+    vllm.multimodal.profiling
+```
+
+### Registry
+
+```{autodoc2-summary}
+    vllm.multimodal.registry
+```
+
+## Model Development
+
+```{autodoc2-summary}
+    vllm.model_executor.models.interfaces_base
+    vllm.model_executor.models.interfaces
+    vllm.model_executor.models.adapters
+```