[Misc] unify variable for LLM instance (#20996)

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

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,
@@ -329,7 +329,7 @@ To this end, we allow registration of default multimodal LoRAs to handle this au
     }
 
 
-    outputs = model.generate(
+    outputs = llm.generate(
         inputs,
         sampling_params=SamplingParams(
             temperature=0.2,

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`: