sync release branch with main (#3229)

* updates in documentation (#3223)

* update requirements in universal-sentence-encoder demo (#3222)

* fix rerank and embeddings demo for windows and gpu (#3235)

Author: dtrawins

demos/common/export_models/export_model.py

@@ -189,7 +189,7 @@ def add_common_arguments(parser):
                 "name": "{{model_name}}_embeddings_model",
                 "base_path": "embeddings",
                 "target_device": "{{target_device|default("CPU", true)}}",
-                "plugin_config": { "NUM_STREAMS": {{num_streams|default("1", true)}} }
+                "plugin_config": { "NUM_STREAMS": "{{num_streams|default(1, true)}}" }
             }
 	}
    ]
@@ -208,7 +208,7 @@ def add_common_arguments(parser):
                 "name": "{{model_name}}_rerank_model",
                 "base_path": "rerank",
                 "target_device": "{{target_device|default("CPU", true)}}",
-                "plugin_config": { "NUM_STREAMS": {{num_streams|default("1", true)}} }
+                "plugin_config": { "NUM_STREAMS": "{{num_streams|default(1, true)}}" }
             }
 	}
    ]

demos/continuous_batching/accuracy/README.md

@@ -80,6 +80,7 @@ export OPENAI_COMPATIBLE_API_URL=http://localhost:8000/v3
 export OPENAI_COMPATIBLE_API_KEY="unused"
 git clone https://github.com/EvolvingLMMs-Lab/lmms-eval
 cd lmms-eval
+git checkout 4471ad311e620ed6cf3a0419d8ba6f18f8fb1cb3  # https://github.com/EvolvingLMMs-Lab/lmms-eval/issues/625
 pip install -e . --extra-index-url "https://download.pytorch.org/whl/cpu"
 python -m lmms_eval \
     --model openai_compatible \
@@ -101,7 +102,7 @@ openai_compatible (model_version=OpenGVLab/InternVL2_5-8B,max_retries=1), gen_kw
 |--------|-------|------|-----:|--------------------|---|--------:|---|------|
 |mme     |Yaml   |none  |     0|mme_cognition_score |↑  | 600.3571|±  |   N/A|
 |mme     |Yaml   |none  |     0|mme_perception_score|↑  |1618.2984|±  |   N/A|
-|mmmu_val|      0|none  |     0|mmmu_acc            |↑  |   0.5100|±  |   N/A|
+|mmmu_val|      0|none  |     0|mmmu_acc            |↑  |   0.5322|±  |   N/A|
 
 ```
 

demos/continuous_batching/vlm/README.md

@@ -46,6 +46,7 @@ python export_model.py text_generation --source_model OpenGVLab/InternVL2_5-8B -
 > **Note:** Change the `--weight-format` to quantize the model to `int8` or `int4` precision to reduce memory consumption and improve performance.
 
 > **Note:** You can change the model used in the demo out of any topology [tested](https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md#visual-language-models) with OpenVINO.
+Be aware that QwenVL models executed on GPU might experience execution errors with very high resolution images. In case of such behavior, it is recommended to reduce the parameter `max_pixels` in `preprocessor_config.json`.
 
 You should have a model folder like below:
 ```

demos/embeddings/README.md

@@ -126,8 +126,7 @@ content-type: application/json
 
 :::{dropdown} **Request embeddings with cURL**
 ```bash
-curl http://localhost:8000/v3/embeddings \
-  -H "Content-Type: application/json" -d '{ "model": "Alibaba-NLP/gte-large-en-v1.5", "input": "hello world"}' | jq .
+curl http://localhost:8000/v3/embeddings -H "Content-Type: application/json" -d "{ \"model\": \"Alibaba-NLP/gte-large-en-v1.5\", \"input\": \"hello world\"}"
 ```
 ```json
 {

demos/rerank/README.md

@@ -106,8 +106,7 @@ content-type: application/json
 :::{dropdown} **Requesting rerank score with cURL**
 
 ```bash
-curl http://localhost:8000/v3/rerank  -H "Content-Type: application/json" \
--d '{ "model": "BAAI/bge-reranker-large", "query": "welcome", "documents":["good morning","farewell"]}' | jq .
+curl http://localhost:8000/v3/rerank  -H "Content-Type: application/json" -d "{ \"model\": \"BAAI/bge-reranker-large\", \"query\": \"welcome\", \"documents\":[\"good morning\",\"farewell\"]}"
 ```
 ```json
 {

demos/universal-sentence-encoder/requirements.txt

@@ -1,2 +1,2 @@
-tensorflow-serving-api==2.11.0
-numpy<2.0.0
+tensorflow-serving-api==2.18.1
+tensorflow==2.18.1