diff --git a/README.md b/README.md
index 299f6667..eeebfcb5 100644
--- a/README.md
+++ b/README.md
@@ -49,7 +49,15 @@ To use [🤗 text-generation-inference](https://github.com/huggingface/text-gene
    ```
    > For gated models such as [LLama](https://huggingface.co/meta-llama) or [StarCoder](https://huggingface.co/bigcode/starcoder), you will have to pass `-e HUGGING_FACE_HUB_TOKEN=<token>` to the `docker run` command above with a valid Hugging Face Hub read token.
 
-    ii. On 8 Gaudi/Gaudi2 cards:
+    ii. On 1 Gaudi/Gaudi2 card using pytorch eager mode with torch compile:
+   ```bash
+   model=meta-llama/Llama-2-7b-hf
+   volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
+
+   docker run -p 8080:80 -v $volume:/data --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e PT_HPU_LAZY_MODE=0 -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.0 --model-id $model --max-input-tokens 1024 --max-total-tokens 2048
+   ```
+
+    iii. On 8 Gaudi/Gaudi2 cards:
    ```bash
    model=meta-llama/Llama-2-70b-hf
    volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
diff --git a/server/text_generation_server/models/causal_lm.py b/server/text_generation_server/models/causal_lm.py
index e701c9c1..f20db570 100644
--- a/server/text_generation_server/models/causal_lm.py
+++ b/server/text_generation_server/models/causal_lm.py
@@ -650,7 +650,7 @@ class CausalLM(Model):
             model = self.prepare_model_for_quantization(model)
             model = model.eval().to(device)
 
-        self.enable_hpu_graph = os.getenv("ENABLE_HPU_GRAPH", "true").lower() == "true"
+        self.enable_hpu_graph = os.getenv("ENABLE_HPU_GRAPH", "true").lower() == "true" and LAZY_MODE == 1
         self.limit_hpu_graph = os.getenv("LIMIT_HPU_GRAPH", "false").lower() == "true"
         model = remove_kv_cache_from_output(model)
         if self.enable_hpu_graph:
@@ -850,6 +850,7 @@ class CausalLM(Model):
             "attention_mask": attention_mask,
             "past_key_values": past_key_values,
             "token_idx": token_idx,
+            "lazy_mode": LAZY_MODE == 1,
         }
 
         if self.has_position_ids: