From 8c5c7f32ddd286b4921bfe5d859e77026c743ccb Mon Sep 17 00:00:00 2001
From: SONG Ge <38711238+sgwhat@users.noreply.github.com>
Date: Wed, 21 Aug 2024 13:45:29 +0800
Subject: [PATCH] Update doc for running npu generate example with
 ipex-llm[npu] (#11876)

* update doc for running npu generate example with ipex-llm[npu]

* switch max_prompt_len to 512 to fix compile error on mtl
---
 .../NPU/HF-Transformers-AutoModels/LLM/README.md      | 11 +++--------
 .../NPU/HF-Transformers-AutoModels/LLM/llama2.py      |  2 +-
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
index 728617f0..6d8fa6f8 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
@@ -32,13 +32,8 @@ We suggest using conda to manage environment:
 conda create -n llm python=3.10
 conda activate llm
 
-# install ipex-llm with 'all' option
-pip install --pre --upgrade ipex-llm[all]
-
-# below command will install intel_npu_acceleration_library
-pip install intel-npu-acceleration-library==1.3
-
-pip install transformers==4.40
+# install ipex-llm with 'npu' option
+pip install --pre --upgrade ipex-llm[npu]
 ```
 
 ### 2. Runtime Configurations
@@ -124,7 +119,7 @@ Arguments info:
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `What is AI?`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
 - `--max-output-len MAX_OUTPUT_LEN`: Defines the maximum sequence length for both input and output tokens. It is default to be `1024`.
-- `--max-prompt-len MAX_PROMPT_LEN`: Defines the maximum number of tokens that the input prompt can contain. It is default to be `768`.
+- `--max-prompt-len MAX_PROMPT_LEN`: Defines the maximum number of tokens that the input prompt can contain. It is default to be `512`.
 
 
 #### Sample Output
diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py
index d23a6405..b9c63c8c 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py
@@ -54,7 +54,7 @@ if __name__ == "__main__":
                         help='Prompt to infer')
     parser.add_argument("--n-predict", type=int, default=32, help="Max tokens to predict")
     parser.add_argument("--max-output-len", type=int, default=1024)
-    parser.add_argument("--max-prompt-len", type=int, default=768)
+    parser.add_argument("--max-prompt-len", type=int, default=512)
     parser.add_argument("--disable-transpose-value-cache", action="store_true", default=False)
     parser.add_argument("--intra-pp", type=int, default=2)
     parser.add_argument("--inter-pp", type=int, default=2)