[Misc] unify variable for LLM instance

Signed-off-by: Andy Xie <andy.xning@gmail.com>

Author: andyxning

docs/configuration/model_resolution.md

@@ -14,7 +14,7 @@ For example:
 ```python
 from vllm import LLM
 
-model = LLM(
+llm = LLM(
     model="cerebras/Cerebras-GPT-1.3B",
     hf_overrides={"architectures": ["GPT2LMHeadModel"]},  # GPT-2
 )

docs/features/lora.md

@@ -302,7 +302,7 @@ To this end, we allow registration of default multimodal LoRAs to handle this au
         return tokenizer.apply_chat_template(chat, tokenize=False)
 
 
-    model = LLM(
+    llm = LLM(
         model=model_id,
         enable_lora=True,
         max_lora_rank=64,

docs/features/quantization/fp8.md

@@ -86,8 +86,9 @@ Load and run the model in `vllm`:
 
 ```python
 from vllm import LLM
-model = LLM("./Meta-Llama-3-8B-Instruct-FP8-Dynamic")
-result = model.generate("Hello my name is")
+
+llm = LLM("./Meta-Llama-3-8B-Instruct-FP8-Dynamic")
+result = llm.generate("Hello my name is")
 print(result[0].outputs[0].text)
 ```
 
@@ -125,9 +126,10 @@ In this mode, all Linear modules (except for the final `lm_head`) have their wei
 
 ```python
 from vllm import LLM
-model = LLM("facebook/opt-125m", quantization="fp8")
+
+llm = LLM("facebook/opt-125m", quantization="fp8")
 # INFO 06-10 17:55:42 model_runner.py:157] Loading model weights took 0.1550 GB
-result = model.generate("Hello, my name is")
+result = llm.generate("Hello, my name is")
 print(result[0].outputs[0].text)
 ```
 

docs/features/quantization/int4.md

@@ -108,7 +108,8 @@ After quantization, you can load and run the model in vLLM:
 
 ```python
 from vllm import LLM
-model = LLM("./Meta-Llama-3-8B-Instruct-W4A16-G128")
+
+llm = LLM("./Meta-Llama-3-8B-Instruct-W4A16-G128")
 ```
 
 To evaluate accuracy, you can use `lm_eval`:

docs/features/quantization/int8.md

@@ -114,7 +114,8 @@ After quantization, you can load and run the model in vLLM:
 
 ```python
 from vllm import LLM
-model = LLM("./Meta-Llama-3-8B-Instruct-W8A8-Dynamic-Per-Token")
+
+llm = LLM("./Meta-Llama-3-8B-Instruct-W8A8-Dynamic-Per-Token")
 ```
 
 To evaluate accuracy, you can use `lm_eval`:

docs/models/pooling_models.md

@@ -149,11 +149,11 @@ You can change the output dimensions of embedding models that support Matryoshka
 ```python
 from vllm import LLM, PoolingParams
 
-model = LLM(model="jinaai/jina-embeddings-v3", 
-            task="embed", 
-            trust_remote_code=True)
-outputs = model.embed(["Follow the white rabbit."], 
-                      pooling_params=PoolingParams(dimensions=32))
+llm = LLM(model="jinaai/jina-embeddings-v3",
+          task="embed",
+          trust_remote_code=True)
+outputs = llm.embed(["Follow the white rabbit."],
+                    pooling_params=PoolingParams(dimensions=32))
 print(outputs[0].outputs)
 ```
 

examples/offline_inference/basic/classify.py

@@ -28,10 +28,10 @@ def main(args: Namespace):
 
     # Create an LLM.
     # You should pass task="classify" for classification models
-    model = LLM(**vars(args))
+    llm = LLM(**vars(args))
 
     # Generate logits. The output is a list of ClassificationRequestOutputs.
-    outputs = model.classify(prompts)
+    outputs = llm.classify(prompts)
 
     # Print the outputs.
     print("\nGenerated Outputs:\n" + "-" * 60)

examples/offline_inference/basic/embed.py

@@ -31,10 +31,10 @@ def main(args: Namespace):
 
     # Create an LLM.
     # You should pass task="embed" for embedding models
-    model = LLM(**vars(args))
+    llm = LLM(**vars(args))
 
     # Generate embedding. The output is a list of EmbeddingRequestOutputs.
-    outputs = model.embed(prompts)
+    outputs = llm.embed(prompts)
 
     # Print the outputs.
     print("\nGenerated Outputs:\n" + "-" * 60)

examples/offline_inference/basic/score.py

@@ -27,10 +27,10 @@ def main(args: Namespace):
 
     # Create an LLM.
     # You should pass task="score" for cross-encoder models
-    model = LLM(**vars(args))
+    llm = LLM(**vars(args))
 
     # Generate scores. The output is a list of ScoringRequestOutputs.
-    outputs = model.score(text_1, texts_2)
+    outputs = llm.score(text_1, texts_2)
 
     # Print the outputs.
     print("\nGenerated Outputs:\n" + "-" * 60)

examples/offline_inference/embed_jina_embeddings_v3.py

@@ -30,11 +30,11 @@ def main(args: Namespace):
 
     # Create an LLM.
     # You should pass task="embed" for embedding models
-    model = LLM(**vars(args))
+    llm = LLM(**vars(args))
 
     # Generate embedding. The output is a list of EmbeddingRequestOutputs.
     # Only text matching task is supported for now. See #16120
-    outputs = model.embed(prompts)
+    outputs = llm.embed(prompts)
 
     # Print the outputs.
     print("\nGenerated Outputs:")