From 2914006fe09875ebfa33626d945e34173c7441c6 Mon Sep 17 00:00:00 2001
From: Reid <61492567+reidliu41@users.noreply.github.com>
Date: Fri, 28 Mar 2025 23:56:48 +0800
Subject: [PATCH] [doc] add missing imports (#15699)

Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
---
 docs/source/models/generative_models.md  | 6 ++++++
 docs/source/models/pooling_models.md     | 8 ++++++++
 docs/source/performance/optimization.md  | 2 ++
 docs/source/serving/multimodal_inputs.md | 8 ++++++++
 docs/source/serving/offline_inference.md | 6 ++++++
 5 files changed, 30 insertions(+)

diff --git a/docs/source/models/generative_models.md b/docs/source/models/generative_models.md
index c94e940b..63fc53b0 100644
--- a/docs/source/models/generative_models.md
+++ b/docs/source/models/generative_models.md
@@ -23,6 +23,8 @@ It is similar to [its counterpart in HF Transformers](https://huggingface.co/doc
 except that tokenization and detokenization are also performed automatically.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="facebook/opt-125m")
 outputs = llm.generate("Hello, my name is")
 
@@ -36,6 +38,8 @@ You can optionally control the language generation by passing {class}`~vllm.Samp
 For example, you can use greedy sampling by setting `temperature=0`:
 
 ```python
+from vllm import LLM, SamplingParams
+
 llm = LLM(model="facebook/opt-125m")
 params = SamplingParams(temperature=0)
 outputs = llm.generate("Hello, my name is", params)
@@ -83,6 +87,8 @@ Base models may perform poorly as they are not trained to respond to the chat co
 :::
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="meta-llama/Meta-Llama-3-8B-Instruct")
 conversation = [
     {
diff --git a/docs/source/models/pooling_models.md b/docs/source/models/pooling_models.md
index f774f3d0..dbcd846c 100644
--- a/docs/source/models/pooling_models.md
+++ b/docs/source/models/pooling_models.md
@@ -68,6 +68,8 @@ The {class}`~vllm.LLM.encode` method is available to all pooling models in vLLM.
 It returns the extracted hidden states directly, which is useful for reward models.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="Qwen/Qwen2.5-Math-RM-72B", task="reward")
 (output,) = llm.encode("Hello, my name is")
 
@@ -81,6 +83,8 @@ The {class}`~vllm.LLM.embed` method outputs an embedding vector for each prompt.
 It is primarily designed for embedding models.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="intfloat/e5-mistral-7b-instruct", task="embed")
 (output,) = llm.embed("Hello, my name is")
 
@@ -96,6 +100,8 @@ The {class}`~vllm.LLM.classify` method outputs a probability vector for each pro
 It is primarily designed for classification models.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="jason9693/Qwen2.5-1.5B-apeach", task="classify")
 (output,) = llm.classify("Hello, my name is")
 
@@ -116,6 +122,8 @@ To handle RAG at a higher level, you should use integration frameworks such as [
 :::
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="BAAI/bge-reranker-v2-m3", task="score")
 (output,) = llm.score("What is the capital of France?",
                       "The capital of Brazil is Brasilia.")
diff --git a/docs/source/performance/optimization.md b/docs/source/performance/optimization.md
index 5b0f8421..ccbe8a36 100644
--- a/docs/source/performance/optimization.md
+++ b/docs/source/performance/optimization.md
@@ -31,6 +31,8 @@ vLLM supports an experimental feature chunked prefill. Chunked prefill allows to
 You can enable the feature by specifying `--enable-chunked-prefill` in the command line or setting `enable_chunked_prefill=True` in the LLM constructor.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="meta-llama/Llama-2-7b-hf", enable_chunked_prefill=True)
 # Set max_num_batched_tokens to tune performance.
 # NOTE: 2048 is the default max_num_batched_tokens for chunked prefill.
diff --git a/docs/source/serving/multimodal_inputs.md b/docs/source/serving/multimodal_inputs.md
index 2e2016c9..f45d36c3 100644
--- a/docs/source/serving/multimodal_inputs.md
+++ b/docs/source/serving/multimodal_inputs.md
@@ -21,6 +21,8 @@ To input multi-modal data, follow this schema in {class}`vllm.inputs.PromptType`
 You can pass a single image to the `'image'` field of the multi-modal dictionary, as shown in the following examples:
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="llava-hf/llava-1.5-7b-hf")
 
 # Refer to the HuggingFace repo for the correct format to use
@@ -65,6 +67,8 @@ Full example: <gh-file:examples/offline_inference/vision_language.py>
 To substitute multiple images inside the same text prompt, you can pass in a list of images instead:
 
 ```python
+from vllm import LLM
+
 llm = LLM(
     model="microsoft/Phi-3.5-vision-instruct",
     trust_remote_code=True,  # Required to load Phi-3.5-vision
@@ -96,6 +100,8 @@ Full example: <gh-file:examples/offline_inference/vision_language_multi_image.py
 Multi-image input can be extended to perform video captioning. We show this with [Qwen2-VL](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) as it supports videos:
 
 ```python
+from vllm import LLM
+
 # Specify the maximum number of frames per video to be 4. This can be changed.
 llm = LLM("Qwen/Qwen2-VL-2B-Instruct", limit_mm_per_prompt={"image": 4})
 
@@ -139,6 +145,8 @@ To input pre-computed embeddings belonging to a data type (i.e. image, video, or
 pass a tensor of shape `(num_items, feature_size, hidden_size of LM)` to the corresponding field of the multi-modal dictionary.
 
 ```python
+from vllm import LLM
+
 # Inference with image embeddings as input
 llm = LLM(model="llava-hf/llava-1.5-7b-hf")
 
diff --git a/docs/source/serving/offline_inference.md b/docs/source/serving/offline_inference.md
index 7bf1c088..2fa19332 100644
--- a/docs/source/serving/offline_inference.md
+++ b/docs/source/serving/offline_inference.md
@@ -11,6 +11,8 @@ For example, the following code downloads the [`facebook/opt-125m`](https://hugg
 and runs it in vLLM using the default configuration.
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="facebook/opt-125m")
 ```
 
@@ -47,6 +49,8 @@ To fix this, explicitly specify the model architecture by passing `config.json`
 For example:
 
 ```python
+from vllm import LLM
+
 model = LLM(
     model="cerebras/Cerebras-GPT-1.3B",
     hf_overrides={"architectures": ["GPT2LMHeadModel"]},  # GPT-2
@@ -92,6 +96,8 @@ You can further reduce memory usage by limiting the context length of the model
 and the maximum batch size (`max_num_seqs` option).
 
 ```python
+from vllm import LLM
+
 llm = LLM(model="adept/fuyu-8b",
           max_model_len=2048,
           max_num_seqs=2)