[Prompt lookup] (openvinotoolkit#1245)

*Description:*
* Implementation of Prompt lookup decoding based on continuous batching
pipeline (cb_promp_lookup_impl + prompt_lookup_impl)
* Update `prompt_lookup_sample` to use new API
* Update statistic to make of printing more usable

*Ticket:*
* https://jira.devtools.intel.com/browse/CVS-137987

*Example of usage:*
* **Input:** `return 0;`
* **Result Prompt lookup:** 
```
=============================== 
Total duration, ms: 3.02267
Draft model duration, ms: 0.000724718
Main model duration, ms: 3.02195
Draft model duration, %: 0.0239761
Main model duration, %: 99.976
AVG acceptance rate, %: 10.8333
=============================== 
Request_id: 0 ||| 0 0 0 0 0 0 0 0 20 20 0 0 0 0 20 100 80 0 0 0 0 0 0 60 0 0 20 0 0 0 0 0 20 0 0 50
```
* **Result Greedy:** 
```
=============================== 
Total duration, ms: 3.18111
Draft model duration, ms: 1.538e-06
Main model duration, ms: 3.18111
Draft model duration, %: 4.83479e-05
Main model duration, %: 100
AVG acceptance rate, %: -nan
===============================
```
* **Speedup**: 100 Generated tokens: 5.24% && 300 Generated tokens: 81%
(9.42 vs 5.19)

---------

Co-authored-by: Ilya Lavrenov <[email protected]>

.github/workflows/causal_lm_cpp.yml

@@ -491,7 +491,6 @@ jobs:
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
           python -m pip install -r ./samples/requirements.txt
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
-          optimum-cli export openvino --trust-remote-code --weight-format fp16 --model Qwen/Qwen-7B-Chat Qwen-7B-Chat --task text-generation-with-past
       - name: run and compare
         run: |
           source ./ov/setupvars.sh
@@ -505,36 +504,22 @@ jobs:
 
           ./build/samples/cpp/prompt_lookup_decoding_lm/prompt_lookup_decoding_lm ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_prompt_lookup.txt
           ./build/samples/cpp/text_generation/greedy_causal_lm ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_greedy.txt
+          python ./samples/python/prompt_lookup_decoding_lm/prompt_lookup_decoding_lm.py ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_py.txt
           python -c "
           with open('predictions_greedy.txt', 'r') as f:
               predicted_greedy = f.readline()
           with open('predictions_prompt_lookup.txt', 'r') as f:
               predicted_prompt_lookup = f.readline()
+          with open('predictions_py.txt', 'r') as f:
+              predicted_prompt_lookup_py = f.readline()
           assert predicted_greedy == predicted_prompt_lookup
+          assert predicted_greedy == predicted_prompt_lookup_py
+          assert predicted_prompt_lookup == predicted_prompt_lookup_py
           "
           echo "Prompt lookup" passed
-      - name: run and compare (model with seq_length_axis = 1)
-        run: |
-          source ./ov/setupvars.sh
-
-          echo 'Code:```python
-          def add(a, b):
-              return a + b
-          ```
-          Question: Can you please add 2 and 3
-          A:' > ./prompt.txt
-
-          ./build/samples/cpp/prompt_lookup_decoding_lm/prompt_lookup_decoding_lm ./Qwen-7B-Chat/ "$(<prompt.txt)" > predictions_prompt_lookup.txt
-          ./build/samples/cpp/text_generation/greedy_causal_lm ./Qwen-7B-Chat/ "$(<prompt.txt)" > predictions_greedy.txt
-          python -c "
-          with open('predictions_greedy.txt', 'r') as f:
-              predicted_greedy = f.readline()
-          with open('predictions_prompt_lookup.txt', 'r') as f:
-              predicted_prompt_lookup = f.readline()
-          assert predicted_greedy == predicted_prompt_lookup
-          "
-          echo "Prompt lookup" passed
-
+        env:
+          PYTHONPATH: "./build/:$PYTHONPATH"
+          LD_LIBRARY_PATH: "./build/openvino_genai/:$LD_LIBRARY_PATH"
   cpp-Phi-1_5:
     runs-on: ubuntu-20.04-16-cores
     defaults:

samples/cpp/prompt_lookup_decoding_lm/CMakeLists.txt

@@ -1,30 +1,23 @@
 # Copyright (C) 2023-2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-find_package(OpenVINO REQUIRED COMPONENTS Runtime Threading)
-
 find_package(OpenVINOGenAI REQUIRED
     PATHS
         "${CMAKE_BINARY_DIR}"  # Reuse the package from the build.
         ${OpenVINO_DIR}  # GenAI may be installed alogside OpenVINO.
     NO_CMAKE_FIND_ROOT_PATH
 )
 
-add_executable(prompt_lookup_decoding_lm prompt_lookup_decoding_lm.cpp)
-target_link_libraries(prompt_lookup_decoding_lm PRIVATE openvino::runtime openvino::threading)
-set_target_properties(prompt_lookup_decoding_lm PROPERTIES
-    COMPILE_PDB_NAME prompt_lookup_decoding_lm
+set(TARGET_NAME prompt_lookup_decoding_lm)
+add_executable(${TARGET_NAME} ${TARGET_NAME}.cpp)
+target_link_libraries(${TARGET_NAME} PRIVATE openvino::genai)
+
+set_target_properties(${TARGET_NAME} PROPERTIES
+    COMPILE_PDB_NAME ${TARGET_NAME} 
     # Ensure out of box LC_RPATH on macOS with SIP
     INSTALL_RPATH_USE_LINK_PATH ON)
-target_compile_features(prompt_lookup_decoding_lm PRIVATE cxx_std_17)
-
-get_target_property(genai_imported openvino::genai IMPORTED_LOCATION)
-set(OPENVINO_TOKENIZERS_PATH $<IF:$<BOOL:${genai_imported}>,${genai_imported},$<TARGET_FILE_DIR:openvino::genai>>)
-set(OPENVINO_TOKENIZERS_FILENAME "${CMAKE_SHARED_LIBRARY_PREFIX}openvino_tokenizers${CMAKE_SHARED_LIBRARY_SUFFIX}")
-target_compile_definitions(prompt_lookup_decoding_lm PRIVATE
-    OPENVINO_TOKENIZERS_PATH="${OPENVINO_TOKENIZERS_PATH}/${OPENVINO_TOKENIZERS_FILENAME}")
 
-install(TARGETS prompt_lookup_decoding_lm
+install(TARGETS ${TARGET_NAME} 
         RUNTIME DESTINATION samples_bin/
         COMPONENT samples_bin
         EXCLUDE_FROM_ALL)