[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (#8973)

Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>

tests/weight_loading/models-large.txt

@@ -3,3 +3,4 @@ compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantize
 compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A16-quantized, main
 compressed-tensors, mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8, main
 gptq_marlin, TheBloke/Mixtral-8x7B-v0.1-GPTQ, main
+awq_marlin, casperhansen/deepseek-coder-v2-instruct-awq, main

tests/weight_loading/run_model_weight_loading_test.sh

@@ -1,7 +1,20 @@
 #!/bin/bash
 SUCCESS=0
 
-IFS=$'\n' read -d '' -r -a MODEL_CONFIGS < "weight_loading/models.txt"
+while getopts "c:" OPT; do
+  case ${OPT} in
+    c ) 
+        CONFIG="$OPTARG"
+        ;;
+    \? )
+        usage
+        exit 1
+        ;;
+  esac
+done
+
+
+IFS=$'\n' read -d '' -r -a MODEL_CONFIGS < $CONFIG
 
 for MODEL_CONFIG in "${MODEL_CONFIGS[@]}"
 do