Merge branch 'main' into benchmarking_script

Author: Jack-Khuu

docs/quantization.md

@@ -142,22 +142,22 @@ To use linear:a8wxdq and embedding:wx, you must set up the torchao experimental
 
 From the torchchat root directory, run
 ```
-sh torchchat/utils/scripts/build_torchao_ops.sh
+bash torchchat/utils/scripts/build_torchao_ops.sh
 ```
 
 This should take about 10 seconds to complete.
 
 Note: if you want to use the new kernels in the AOTI and C++ runners, you must pass the flag link_torchao_ops when running the scripts the build the runners.
 
 ```
-sh torchchat/utils/scripts/build_native.sh aoti link_torchao_ops
+bash torchchat/utils/scripts/build_native.sh aoti link_torchao_ops
 ```
 
 ```
-sh torchchat/utils/scripts/build_native.sh et link_torchao_ops
+bash torchchat/utils/scripts/build_native.sh et link_torchao_ops
 ```
 
-Note before running `sh torchchat/utils/scripts/build_native.sh et link_torchao_ops`, you must first install executorch with `sh torchchat/utils/scripts/install_et.sh` if you have not done so already.
+Note before running `bash torchchat/utils/scripts/build_native.sh et link_torchao_ops`, you must first install executorch with `bash torchchat/utils/scripts/install_et.sh` if you have not done so already.
 
 ### Examples
 
@@ -212,7 +212,7 @@ Currently, torchchat can only run them on Eager mode.
 
 From the torchchat root directory, run
 ```
-sh torchchat/utils/scripts/build_torchao_ops.sh mps
+bash torchchat/utils/scripts/build_torchao_ops.sh mps
 ```
 
 ### Examples

torchchat/utils/quantize.py

@@ -934,15 +934,15 @@ def quantized_model(self) -> nn.Module:
         torch.ops.load_library(libs[0])
         print("Loaded torchao cpu ops.")
     except Exception as e:
-        print("Unabled to load torchao cpu ops library. Slow fallback kernels will be used.")
+        print("Unable to load torchao cpu ops library. Slow fallback kernels will be used.")
 
     try:
         libname = "libtorchao_ops_mps_aten.dylib"
         libpath = f"{torchao_build_path}/cmake-out/lib/{libname}"
         torch.ops.load_library(libpath)
         print("Loaded torchao mps ops.")
     except Exception as e:
-        print("Unabled to load torchao mps ops library.")
+        print("Unable to load torchao mps ops library.")
 
 except Exception as e:
     print("Unabled to import torchao experimental quant_api with error: ", e)

torchchat/utils/scripts/updown.py

@@ -267,6 +267,8 @@ def updown_processor(
         lines = file.readlines()
     print_flag = False
 
+    # Use bash; set it to fail on the first failing command
+    output("#! /bin/bash", replace_list=None, suppress_list=None)
     output("set -eou pipefail", replace_list=None, suppress_list=None)
 
     if create_sections: