[Tests]: Adding dummy causal models for testing in regular CI run (#427)

### Purpose of this PR:
This update aims to reduce test execution time for causal language model
inference. Previously, tests were run using full-scale models with one
or two layers, which was inefficient and time-consuming. Refactoring CLI
api testing for independent testing and redundant conftest code.

### What’s Changed:
Introduced dummy models with significantly smaller configurations by
adjusting parameters such as `max_position_embeddings,
num_hidden_layers, num_attention_heads, hidden_size, intermediate_size,
vocab_size and additional_params`.
These lightweight models are used exclusively for testing purposes to
ensure faster execution without compromising test coverage.

And CLI testing has two test scripts one is for export, compile, and
execute, another is for infer cli api.

**Note:** This optimization is applied only to causal language models.

---------

Signed-off-by: Abukhoyer Shaik <[email protected]>

Author: abukhoy

QEfficient/utils/test_utils.py

@@ -150,3 +150,24 @@ def __call__(
             image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
             query = query.replace("<image>", image_tokens, 1)
         return query
+
+
+class ModelConfig:
+    """
+    Contains all the model types which are not default model like quantized models, external models, swiftkv models etc,.
+    """
+
+    QUANTIZED_MODELS = {
+        "neuralmagic/Qwen2-0.5B-Instruct-FP8",
+        "neuralmagic/Llama-3.2-3B-Instruct-FP8",
+        "TheBloke/Llama-2-7B-GPTQ",
+        "TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ",
+    }
+
+    EXTERNAL_MODELS = {
+        "hpcai-tech/grok-1",
+    }
+
+    SWIFTKV_MODELS = {
+        "Snowflake/Llama-3.1-SwiftKV-8B-Instruct",
+    }

scripts/Jenkinsfile

@@ -59,7 +59,7 @@ pipeline {
                            mkdir -p $PWD/Non_qaic &&
                            export TOKENIZERS_PARALLELISM=false &&
                            export QEFF_HOME=$PWD/Non_qaic &&
-                           pytest tests -m '(not cli) and (on_qaic) and (not multimodal) and (not qnn) and (not finetune)' --ignore tests/vllm -n 4 --junitxml=tests/tests_log2.xml &&
+                           pytest tests -m '(not cli) and (on_qaic) and (not nightly) and (not multimodal) and (not qnn) and (not finetune)' --ignore tests/vllm -n 4 --junitxml=tests/tests_log2.xml &&
                            junitparser merge tests/tests_log2.xml tests/tests_log.xml &&
                            deactivate"
                            '''
@@ -97,7 +97,7 @@ pipeline {
                            mkdir -p $PWD/cli &&
                            export TOKENIZERS_PARALLELISM=false &&
                            export QEFF_HOME=$PWD/cli &&
-                           pytest tests -m '(cli and not qnn) and (not finetune)' --ignore tests/vllm --junitxml=tests/tests_log3.xml &&
+                           pytest tests -m '(cli and not qnn) and (not finetune)' --ignore tests/vllm -n 4 --junitxml=tests/tests_log3.xml &&
                            junitparser merge tests/tests_log3.xml tests/tests_log.xml &&
                            deactivate"
                            '''
@@ -126,7 +126,7 @@ pipeline {
                     mkdir -p $PWD/Qnn_cli &&
                     export TOKENIZERS_PARALLELISM=false &&
                     export QEFF_HOME=$PWD/Qnn_cli &&
-                    pytest tests -m '(cli and qnn) and (not finetune)' --ignore tests/vllm --junitxml=tests/tests_log4.xml &&
+                    pytest tests -m '(cli and qnn) and (not finetune)' --ignore tests/vllm -n 4 --junitxml=tests/tests_log4.xml &&
                     junitparser merge tests/tests_log4.xml tests/tests_log.xml &&
                     deactivate"
                     '''
@@ -145,7 +145,7 @@ pipeline {
                     mkdir -p $PWD/Qnn_non_cli &&
                     export TOKENIZERS_PARALLELISM=false &&
                     export QEFF_HOME=$PWD/Qnn_non_cli &&
-                    pytest tests -m '(not cli) and (qnn) and (on_qaic) and (not multimodal) and (not finetune)' --ignore tests/vllm --junitxml=tests/tests_log5.xml &&
+                    pytest tests -m '(not cli) and (qnn) and (not nightly) and (on_qaic) and (not multimodal) and (not finetune)' --ignore tests/vllm -n 4 --junitxml=tests/tests_log5.xml &&
                     junitparser merge tests/tests_log5.xml tests/tests_log.xml &&
                     deactivate"
                     '''