diff --git a/llama_toolchain/configs/ashwin.yaml b/llama_toolchain/configs/ashwin.yaml
deleted file mode 100644
index 21ab6b880..000000000
--- a/llama_toolchain/configs/ashwin.yaml
+++ /dev/null
@@ -1,11 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/ashwin/local/checkpoints/Meta-Llama-3.1-70B-Instruct-20240710150000
-    tokenizer_path: /home/ashwin/local/checkpoints/Meta-Llama-3.1-70B-Instruct-20240710150000/tokenizer.model
-    model_parallel_size: 8
-    max_seq_len: 2048
-    max_batch_size: 1
-    quantization:
-      type: "fp8"
diff --git a/llama_toolchain/configs/chrisluc.yaml b/llama_toolchain/configs/chrisluc.yaml
deleted file mode 100644
index c44f9524e..000000000
--- a/llama_toolchain/configs/chrisluc.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/chrisluc/models/Meta-Llama-3.1-8B-Instruct-20240710150000
-    tokenizer_path: /home/chrisluc/models/Meta-Llama-3.1-8B-Instruct-20240710150000/tokenizer.model
-    model_parallel_size: 1
-    max_seq_len: 2048
-    max_batch_size: 1
diff --git a/llama_toolchain/configs/cyni.yaml b/llama_toolchain/configs/cyni.yaml
deleted file mode 100644
index e8edbf036..000000000
--- a/llama_toolchain/configs/cyni.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/cyni/local/llama-3
-    tokenizer_path: /home/cyni/local/llama-3/cl_toplang_128k
-    model_parallel_size: 1
-    max_seq_len: 2048
-    max_batch_size: 1
diff --git a/llama_toolchain/configs/default.yaml b/llama_toolchain/configs/default.yaml
deleted file mode 100644
index d13f37226..000000000
--- a/llama_toolchain/configs/default.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/dalton/models/Meta-Llama-3.1-8B-Instruct-20240710150000
-    tokenizer_path: /home/dalton/models/Meta-Llama-3.1-8B-Instruct-20240710150000/tokenizer.model
-    model_parallel_size: 1
-    max_seq_len: 2048
-    max_batch_size: 1
diff --git a/llama_toolchain/configs/hjshah.yaml b/llama_toolchain/configs/hjshah.yaml
deleted file mode 100644
index 089ab1b5a..000000000
--- a/llama_toolchain/configs/hjshah.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/hjshah/local/checkpoints/Meta-Llama-3.1-8B-Instruct-20240710150000
-    tokenizer_path: /home/hjshah/local/checkpoints/Meta-Llama-3.1-8B-Instruct-20240710150000/tokenizer.model
-    model_parallel_size: 1
-    max_seq_len: 2048
-    max_batch_size: 1
diff --git a/llama_toolchain/configs/long_seqlen.yaml b/llama_toolchain/configs/long_seqlen.yaml
deleted file mode 100644
index 9eaeab1bd..000000000
--- a/llama_toolchain/configs/long_seqlen.yaml
+++ /dev/null
@@ -1,9 +0,0 @@
-inference_config:
-  impl_type: "inline"
-  inline_config:
-    checkpoint_type: "pytorch"
-    checkpoint_dir: /home/hjshah/local/checkpoints/Meta-Llama-3.1-8B-Instruct-20240710150000
-    tokenizer_path: /home/hjshah/local/checkpoints/Meta-Llama-3.1-8B-Instruct-20240710150000/tokenizer.model
-    model_parallel_size: 1
-    max_seq_len: 8192
-    max_batch_size: 1
diff --git a/llama_toolchain/inference/client.py b/llama_toolchain/inference/client.py
index 2e8a36161..c798ed6fe 100644
--- a/llama_toolchain/inference/client.py
+++ b/llama_toolchain/inference/client.py
@@ -18,6 +18,7 @@ from .event_logger import EventLogger
 
 class InferenceClient(Inference):
     def __init__(self, base_url: str):
+        print(f"Initializing client for {base_url}")
         self.base_url = base_url
 
     async def initialize(self) -> None: