add readme

python/llm/example/GPU/Pipeline-Parallel-Inference/README.md

@@ -12,6 +12,7 @@ To run this example with IPEX-LLM on Intel GPUs, we have some recommended requir
 - [Qwen/Qwen1.5-7B-Chat](./run_qwen1.5_arc_2_card.sh)
 - [Qwen/Qwen1.5-14B-Chat](./run_qwen1.5_arc_2_card.sh)
 - [Qwen/Qwen1.5-32B-Chat](./run_qwen1.5_arc_2_card.sh)
+- [THUDM/chatglm3-6b](./run_chatglm_arc_2_card.sh)
 - [baichuan-inc/Baichuan2-7B-Chat](./run_baichuan2_arc_2_card.sh)
 - [baichuan-inc/Baichuan2-13B-Chat](./run_baichuan2_arc_2_card.sh)
 - [microsoft/Phi-3-mini-4k-instruct](./run_phi3_arc_2_card.sh)
@@ -71,6 +72,21 @@ bash run_qwen1.5_arc_2_card.sh
 
 </details>
 
+<details>
+  <summary> Show chatglm example </summary>
+
+#### Run chatglm3-6B on two Intel Arc A770
+
+You could specify `--repo-id-or-model-path` in the test script to be the huggingface repo id for chatglm to be downloaded, or the path to the huggingface checkpoint folder. Besides, you could change `NUM_GPUS` to the number of GPUs you have on your machine.
+
+```bash
+bash run_chatglm_arc_2_card.sh
+```
+
+</details>
+
+</details>
+
 <details>
   <summary> Show Baichuan2 example </summary>