diff --git a/README.md b/README.md
index bf9a9f20..fc5be00d 100644
--- a/README.md
+++ b/README.md
@@ -22,22 +22,12 @@ limitations under the License.
   - [Table of contents](#table-of-contents)
   - [Tested Models and Configurations](#tested-models-and-configurations)
   - [Running TGI on Gaudi](#running-tgi-on-gaudi)
-    - [TGI-Gaudi Benchmark](#tgi-gaudi-benchmark)
-      - [Static Batching Benchmark](#static-batching-benchmark)
-      - [Continuous Batching Benchmark](#continuous-batching-benchmark)
-    - [Tested Models and Configurations](#tested-models-and-configurations)
   - [Running TGI with BF16 Precision](#running-tgi-with-bf16-precision)
-    - [Llama2-7B on 1 Card](#llama2-7b-on-1-card)
-    - [Llama2-70B on 8 cards](#llama2-70b-on-8-cards)
-    - [Llama3.1-8B on 1 card](#llama31-8b-on-1-card)
-    - [Llama3.1-70B 8 cards](#llama31-70b-8-cards)
-    - [Llava-v1.6-Mistral-7B on 1 card](#llava-v16-mistral-7b-on-1-card)
   - [Running TGI with FP8 Precision](#running-tgi-with-fp8-precision)
   - [TGI-Gaudi Benchmark](#tgi-gaudi-benchmark)
   - [Adjusting TGI Parameters](#adjusting-tgi-parameters)
   - [Environment Variables](#environment-variables)
   - [Profiler](#profiler)
-  - [License](#license)
 
 
 ## Tested Models and Configurations
diff --git a/server/text_generation_server/server.py b/server/text_generation_server/server.py
index 11a7d7a6..bc458a91 100644
--- a/server/text_generation_server/server.py
+++ b/server/text_generation_server/server.py
@@ -104,14 +104,6 @@ class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer):
 
         max_supported_total_tokens = self.model.warmup(request)
         return generate_pb2.WarmupResponse(max_supported_total_tokens=max_supported_total_tokens)
-        # else:
-        #     batch = self.model.batch_type.from_pb(
-        #         request.batch, self.model.tokenizer, self.model.dtype, self.model.device
-        #     )
-
-        #     max_supported_total_tokens = self.model.warmup(batch)
-        #     return generate_pb2.WarmupResponse(max_supported_total_tokens=max_supported_total_tokens)
-
 
     async def Prefill(self, request, context):
         start = time.time_ns()