Merge pull request #66 from vkuzo/20251002_refactor_2

clean up hf scripts

Author: vkuzo

hf_torchao_vllm/torchao_hf_script.py renamed to hf_torchao_vllm/quantize_hf_model_with_torchao.py

@@ -2,10 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 """
-Script for quantizing LLM models with TorchAO.
+Script for quantizing HuggingFace models with TorchAO.
 Supports various quantization configurations and model types.
-
-Copy of Driss's https://www.internalfb.com/phabricator/paste/view/P1838316614
 """
 
 

hf_torchao_vllm/run_vllm.py renamed to hf_torchao_vllm/run_quantized_model_in_vllm.py

@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
 
-# copied from Driss's https://www.internalfb.com/phabricator/paste/view/P1858050926
-
 import os
 
 import random