Update README.md

README.md

@@ -48,9 +48,11 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## Benchmark Results
 
-Benchmarked on a single NVIDIA A100 40GB GPU using:
-- Transformers backend (FP16 and INT8 variants). However, The current implementation of transformers does not include optimized kernels to support int8 computation directly.
-- vLLM engine for INT8 inference acceleration
+- Benchmarked on a single NVIDIA A100 40GB GPU using:
+  - Transformers backend (FP16 and INT8 variants). Note: The current implementation of `transformers` does not include optimized kernels for direct INT8 computation.
+  - vLLM engine with INT8 inference acceleration for improved performance.
+
+ 
 ---
 
 | Metric             | Transformers (INT8) | Transformers (FP16) | vLLM (INT8)        |