Skip to content

[DO NOT MERGE] common params attempt #1 #1503

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

[DO NOT MERGE] common params attempt #1 #1503

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7ba906b
common params attempt #1
ljaljushkin Oct 30, 2025
e34e54d
Update optimum/intel/openvino/configuration.py
nikita-savelyevv Oct 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 40 additions & 10 deletions optimum/intel/openvino/configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,7 +100,7 @@ class OVQuantizationMethod(str, Enum):
"Qwen/Qwen-7B-Chat": {"bits": 4, "sym": True, "group_size": 128, "ratio": 0.6},
"Qwen/Qwen2.5-1.5B-Instruct": {
"bits": 4,
"sym": False,
"sym": True,
"group_size": 128,
"ratio": 0.9,
"dataset": "wikitext2",
Expand Down Expand Up @@ -140,7 +140,7 @@ class OVQuantizationMethod(str, Enum):
},
"Qwen/Qwen3-8B": {
"bits": 4,
"sym": False,
"sym": True,
"group_size": 128,
"ratio": 1.0,
"dataset": "wikitext2",
Expand Down Expand Up @@ -233,8 +233,8 @@ class OVQuantizationMethod(str, Enum):
},
"meta-llama/Meta-Llama-3.1-8B-Instruct": {
"bits": 4,
"sym": False,
"group_size": 64,
"sym": True,
"group_size": 128,
"ratio": 0.8,
"quant_method": OVQuantizationMethod.AWQ,
},
Expand Down Expand Up @@ -262,11 +262,42 @@ class OVQuantizationMethod(str, Enum):
},
"microsoft/Phi-3.5-mini-instruct": {
"bits": 4,
"sym": False,
"group_size": 64,
"sym": True,
"group_size": 128,
"ratio": 1.0,
"quant_method": OVQuantizationMethod.AWQ,
},
"microsoft/Phi-4-reasoning": {
"bits": 4,
"sym": True,
"group_size": 128,
"ratio": 1.0,
"quant_method": OVQuantizationMethod.AWQ,
},
"google/gemma-3-4b-it": {
"bits": 4,
"sym": True,
"group_size": 128,
"ratio": 1.0,
},
"Mistral-7B-Instruct-v0.2": {
"bits": 4,
"sym": True,
"group_size": 128,
"ratio": 1.0,
},
"openbmb/MiniCPM4-0.5B": {
"bits": 4,
"sym": True,
"group_size": 128,
"ratio": 1.0,
},
"openbmb/MiniCPM4-8B": {
"bits": 4,
"sym": True,
"group_size": 128,
"ratio": 1.0,
},
"microsoft/Phi-4-mini-instruct": {
"bits": 4,
"sym": False,
Expand All @@ -290,10 +321,9 @@ class OVQuantizationMethod(str, Enum):
},
"deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
"bits": 4,
"sym": False,
"group_size": 64,
"ratio": 0.8,
"quant_method": OVQuantizationMethod.AWQ,
"sym": True,
"group_size": 128,
"ratio": 1,
},
"microsoft/Phi-4-multimodal-instruct": {
"quantization_configs": {
Expand Down
Loading