[Misc] rename torch_dtype to dtype (#26695)

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

docs/features/quantization/auto_round.md

@@ -58,7 +58,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from auto_round import AutoRound
 
 model_name = "Qwen/Qwen3-0.6B"
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto")
+model = AutoModelForCausalLM.from_pretrained(model_name, dtype="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 bits, group_size, sym = 4, 128, True

docs/features/quantization/fp8.md

@@ -43,7 +43,7 @@ MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    torch_dtype="auto",
+    dtype="auto",
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 ```

docs/features/quantization/int4.md

@@ -41,7 +41,7 @@ MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    torch_dtype="auto",
+    dtype="auto",
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 ```

docs/features/quantization/int8.md

@@ -46,7 +46,7 @@ MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    torch_dtype="auto",
+    dtype="auto",
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 ```

docs/features/quantization/quantized_kvcache.md

@@ -82,7 +82,7 @@ Here's a complete example using `meta-llama/Llama-3.1-8B-Instruct` (most models
 
     # Select model and load it
     MODEL_ID = "meta-llama/Llama-3.1-8B-Instruct"
-    model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto")
+    model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto", dtype="auto")
     tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
     # Select calibration dataset

docs/features/quantization/quark.md

@@ -50,7 +50,7 @@ to fetch model and tokenizer.
     model = AutoModelForCausalLM.from_pretrained(
         MODEL_ID,
         device_map="auto",
-        torch_dtype="auto",
+        dtype="auto",
     )
     model.eval()
 

docs/features/quantization/torchao.md

@@ -27,7 +27,7 @@ You can quantize your own huggingface model with torchao, e.g. [transformers](ht
     quantization_config = TorchAoConfig(Int8WeightOnlyConfig())
     quantized_model = AutoModelForCausalLM.from_pretrained(
         model_name,
-        torch_dtype="auto",
+        dtype="auto",
         device_map="auto",
         quantization_config=quantization_config
     )