[Upgradation]: onnx opset version updated from 13 to 17 (#587)

This pull request is created for updating the _onnx opset_ version to 17
from 13.

## Testing
Below are the models I have tested:
### Causal Models
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
- gpt2
- Salesforce/codegen-350M-mono
- microsoft/Phi-3-mini-4k-instruct
- tiiuae/falcon-7b
- Qwen/Qwen2-0.5B
- Qwen/Qwen3-0.6B
- bigcode/starcoder2-3b
- Qwen/Qwen3-30B-A3B-Instruct-2507
- Felladrin/Minueza-32M-Base
- wtang06/mpt-125m-c4
- hakurei/gpt-j-random-tinier
- mistralai/Mixtral-8x7B-Instruct-v0.1
- meta-llama/Llama-3.2-1B
- unsloth/gemma-2b
- unsloth/gemma-2-2b
- TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ
- TheBloke/Llama-2-7B-GPTQ
- ibm-granite/granite-20b-code-base
- neuralmagic/Llama-3.2-3B-Instruct-FP8
- neuralmagic/Qwen2-0.5B-Instruct-FP8
- ibm-granite/granite-3.1-2b-instruct
- ibm-granite/granite-guardian-3.1-2b
- hpcai-tech/grok-1
- Snowflake/Llama-3.1-SwiftKV-8B-Instruct
- allenai/OLMo-2-0425-1B

### Embedding Models
- BAAI/bge-base-en-v1.5
- BAAI/bge-large-en-v1.5
- BAAI/bge-small-en-v1.5
- intfloat/e5-large-v2
- sentence-transformers/multi-qa-mpnet-base-cos-v1
- ibm-granite/granite-embedding-30m-english
- ibm-granite/granite-embedding-125m-english
- BAAI/bge-reranker-v2-m3
- ibm-granite/granite-embedding-107m-multilingual
- ibm-granite/granite-embedding-278m-multilingual

### Vision Models
- llava-hf/llava-1.5-7b-hf
- OpenGVLab/InternVL2_5-1B
- meta-llama/Llama-3.2-11B-Vision-Instruct
- ibm-granite/granite-vision-3.2-2b
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- google/gemma-3-4b-it

### Audio Models
- openai/whisper-tiny
- openai/whisper-base
- openai/whisper-small
- openai/whisper-medium
- openai/whisper-large
- openai/whisper-large-v3-turbo

---------

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

Author: abukhoy

QEfficient/exporter/export_utils.py

@@ -18,6 +18,7 @@
 from onnx import external_data_helper
 
 from QEfficient.base.onnx_transforms import FP16ClipTransform
+from QEfficient.utils import constants
 
 
 def export_onnx(
@@ -97,7 +98,7 @@ def export_onnx(
             input_names=input_names,
             output_names=output_names,
             dynamic_axes=dynamic_axes,
-            opset_version=13,
+            opset_version=constants.ONNX_EXPORT_OPSET,
             custom_opsets={"com.qti.aisw.onnx": 1},
         )
     except Exception as e:

QEfficient/utils/constants.py

@@ -17,7 +17,6 @@
 ONNX_EXPORT_EXAMPLE_SEQ_LEN = 32
 ONNX_EXPORT_EXAMPLE_FBS = 4
 ONNX_EXPORT_EXAMPLE_NLK = 2  # Number of Logits to Keep
-ONNX_EXPORT_OPSET = 13
 ONNX_EXPORT_MAX_NUM_IMAGES = 1
 ONNX_EXPORT_MAX_IMAGE_TILES = 4
 ONNX_EXPORT_IMAGE_WIDTH = 560
@@ -84,7 +83,7 @@ def get_models_dir():
 ONNX_EXPORT_EXAMPLE_MAX_TOP_K_IDS = 512
 ONNX_EXPORT_EXAMPLE_TOP_PS = 0.80
 ONNX_EXPORT_EXAMPLE_MIN_PS = 0.99
-ONNX_EXPORT_OPSET = 13
+ONNX_EXPORT_OPSET = 17
 
 COMPILER = ["/opt/qti-aic/exec/qaic-exec", "-aic-hw"]
 DEFAULT_AIC_HW_VERSION = "ai100"