Fixed linting issues with QAT Notebook

Signed-off-by: Farshad Ghodsian <[email protected]>

Author: farshadghodsian

examples/llm_qat/notebooks/QAT_QAD_Walkthrough.ipynb

@@ -608,6 +608,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%sh # [run in command line outside notebook]\n",
+    "\n",
     "docker run --rm --ipc=host -it \\\n",
     "  --ulimit stack=67108864   --ulimit memlock=-1 \\\n",
     "  --gpus all   -p 8000:8000   -e TRTLLM_ENABLE_PDL=1 \\\n",
@@ -640,6 +642,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%sh # [run in TensorRT-LLM container]\n",
+    "\n",
     "git clone https://github.com/NVIDIA/TensorRT-Model-Optimizer.git"
    ]
   },
@@ -658,6 +662,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%sh # [run in TensorRT-LLM container]\n",
+    "\n",
     "cd TensorRT-Model-Optimizer/\n",
     "pip install -e ."
    ]
@@ -679,6 +685,8 @@
    },
    "outputs": [],
    "source": [
+    "%%sh # [run in TensorRT-LLM container]\n",
+    "\n",
     "# set export path for converted checkpoints. The script saves the converted checkpoint in ${ROOT_SAVE_PATH}/saved_models_${MODEL_FULL_NAME}\n",
     "export ROOT_SAVE_PATH=/app/tensorrt_llm\n",
     "\n",
@@ -710,6 +718,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%sh # [run in TensorRT-LLM container]\n",
+    "\n",
     "trtllm-serve /app/tensorrt_llm/saved_models_checkpoint-450_nvfp4_hf/  \\\n",
     "  --max_batch_size 1 --max_num_tokens 1024 \\\n",
     "  --max_seq_len 4096 --tp_size 8 --pp_size 1 \\\n",
@@ -803,7 +813,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "fb78741b-30cb-46f2-a292-c5192cbca9ed",
    "metadata": {},
    "outputs": [