[DOCS] fix typo in npu llm inference guide and update wwb link (#28365)

### Details:
 - *fixed optimum-cli arguments formatting in NPU llm inference guide*
- *updated link for who_what_benchmark* that was moved to tools
directory sometime ago

docs/articles_en/learn-openvino/llm_inference_guide/genai-guide-npu.rst

@@ -44,7 +44,7 @@ You select one of the methods by setting the ``--group-size`` parameter to eithe
       .. code-block:: console
          :name: group-quant
 
-         optimum-cli export openvino -m TinyLlama/TinyLlama-1.1B-Chat-v1.0 --weight-format int4 --sym --ratio 1.0 --group_size 128 TinyLlama-1.1B-Chat-v1.0
+         optimum-cli export openvino -m TinyLlama/TinyLlama-1.1B-Chat-v1.0 --weight-format int4 --sym --ratio 1.0 --group-size 128 TinyLlama-1.1B-Chat-v1.0
 
    .. tab-item:: Channel-wise quantization
 
@@ -63,12 +63,12 @@ You select one of the methods by setting the ``--group-size`` parameter to eithe
             If you want to improve accuracy, make sure you:
 
             1. Update NNCF: ``pip install nncf==2.13``
-            2. Use ``--scale_estimation --dataset=<dataset_name>`` and accuracy aware quantization ``--awq``:
+            2. Use ``--scale_estimation --dataset <dataset_name>`` and accuracy aware quantization ``--awq``:
 
                .. code-block:: console
                   :name: channel-wise-data-aware-quant
 
-                  optimum-cli export openvino -m meta-llama/Llama-2-7b-chat-hf --weight-format int4 --sym --group-size -1 --ratio 1.0 --awq --scale-estimation --dataset=wikitext2  Llama-2-7b-chat-hf
+                  optimum-cli export openvino -m meta-llama/Llama-2-7b-chat-hf --weight-format int4 --sym --group-size -1 --ratio 1.0 --awq --scale-estimation --dataset wikitext2  Llama-2-7b-chat-hf
 
 
       .. important::

docs/articles_en/openvino-workflow/model-optimization-guide/weight-compression.rst

@@ -354,7 +354,7 @@ To find the optimal weight compression parameters for a particular model, refer
 `example <https://github.com/openvinotoolkit/nncf/tree/develop/examples/llm_compression/openvino/tiny_llama_find_hyperparams>`__ ,
 where weight compression parameters are being searched from the subset of values.
 To speed up the search, a self-designed validation pipeline called
-`WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/llm_bench/python/who_what_benchmark>`__
+`WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/tools/who_what_benchmark>`__
 is used. The pipeline can quickly evaluate the changes in the accuracy of the optimized
 model compared to the baseline.
 
@@ -491,7 +491,7 @@ Additional Resources
 - `OpenVINO GenAI Repo <https://github.com/openvinotoolkit/openvino.genai>`__
   : Repository containing example pipelines that implement image and text generation
   tasks. It also provides a tool to benchmark LLMs.
-- `WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/llm_bench/python/who_what_benchmark>`__
+- `WhoWhatBench <https://github.com/openvinotoolkit/openvino.genai/tree/master/tools/who_what_benchmark>`__
 - `NNCF GitHub <https://github.com/openvinotoolkit/nncf>`__
 - :doc:`Post-training Quantization <quantizing-models-post-training>`
 - :doc:`Training-time Optimization <compressing-models-during-training>`