Update README and wordlist

benchmarks/inference_throughput/cloud-api/README.md

@@ -20,5 +20,5 @@ Note that the API endpoint might implemented a rate limit for token generation i
 Once everything configured, to run chat model benchmark:  
 ```python chat_azure_api_benchmark.py```
 
-To run pretrained model benchamrk:
+To run pretrained model benchmark:
 ```python pretrained_azure_api_benchmark.py```

scripts/spellcheck_conf/wordlist.txt

@@ -1216,4 +1216,5 @@ Anyscale
 ADDR
 ckpt
 HuggingFace
-llamaguard
+llamaguard
+LEVELs