[Gaudi] Fix the integration-test issues (#3265)

Signed-off-by: yuanwu <yuan.wu@intel.com>

Author: yuanwu2017

backends/gaudi/Makefile

@@ -50,13 +50,15 @@ local-dev-install: install-dependencies
 
 # In order to run the integration tests, you need to first build the image (make -C backends/gaudi image)
 run-integration-tests:
+	pip install -U pip uv
 	uv pip install -r ${root_dir}/backends/gaudi/server/integration-tests/requirements.txt
 	DOCKER_VOLUME=${root_dir}/data \
 	HF_TOKEN=`cat ${HOME}/.cache/huggingface/token` \
 	uv run pytest --durations=0 -sv ${root_dir}/backends/gaudi/server/integration-tests
 
 # This is used to capture the expected outputs for the integration tests offering an easy way to add more models to the integration tests
 capture-expected-outputs-for-integration-tests:
+	pip install -U pip uv
 	DOCKER_VOLUME=${root_dir}/data \
 	HF_TOKEN=`cat ${HOME}/.cache/huggingface/token` \
 	uv run pytest --durations=0 -sv ${root_dir}/backends/gaudi/server/integration-tests/capture_expected_outputs.py

backends/gaudi/server/integration-tests/test_model.py

@@ -9,8 +9,8 @@
     "meta-llama/Llama-3.1-8B-Instruct-shared": {
         "model_id": "meta-llama/Llama-3.1-8B-Instruct",
         "input": "What is Deep Learning?",
-        "expected_greedy_output": " A Beginner’s Guide\nDeep learning is a subset of machine learning that involves the use",
-        "expected_batch_output": " A Beginner’s Guide\nDeep learning is a subset of machine learning that involves the use",
+        "expected_greedy_output": " A Beginner’s Guide\nDeep learning is a subset of machine learning that involves the use of artificial neural networks to analyze and interpret data. It is a type of",
+        "expected_batch_output": " A Beginner’s Guide\nDeep learning is a subset of machine learning that involves the use of artificial neural networks to analyze and interpret data. It is a type of",
         "args": [
             "--sharded",
             "true",
@@ -165,20 +165,6 @@
             "4",
         ],
     },
-    "facebook/opt-125m": {
-        "model_id": "facebook/opt-125m",
-        "input": "What is Deep Learning?",
-        "expected_greedy_output": "\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout",
-        "expected_batch_output": "\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout the Author\n\nAbout",
-        "args": [
-            "--max-input-tokens",
-            "512",
-            "--max-total-tokens",
-            "1024",
-            "--max-batch-size",
-            "4",
-        ],
-    },
     "EleutherAI/gpt-j-6b": {
         "model_id": "EleutherAI/gpt-j-6b",
         "input": "What is Deep Learning?",

backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py

@@ -111,6 +111,7 @@ def __init__(self, prefix: str, config, weights, layer_id):
         )
         self.num_heads = config.num_attention_heads
         self.hidden_size = config.hidden_size
+
         if getattr(config, "head_dim", None) is not None:
             self.head_size = config.head_dim
         else: