Skip to content

[OpenVINO]add support for minicpmv4/4_5 #1412

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

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

[OpenVINO]add support for minicpmv4/4_5 #1412

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
4b70b7f
add support for minicpm4v
openvino-dev-samples Aug 7, 2025
7c64417
reformat
openvino-dev-samples Aug 7, 2025
4b245f1
add minicpmv4 test case
openvino-dev-samples Aug 12, 2025
81f69be
add minicpmv4_5
openvino-dev-samples Aug 27, 2025
6974a3e
rebase
openvino-dev-samples Sep 27, 2025
bd8b41f
update minicpm4/4.5 CI test
openvino-dev-samples Oct 16, 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
16 changes: 13 additions & 3 deletions optimum/exporters/openvino/model_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2625,12 +2625,22 @@ def with_behavior(
"""
if isinstance(behavior, str) and not isinstance(behavior, MiniCPMVConfigBehavior):
behavior = MiniCPMVConfigBehavior(behavior)

model_mapping = {2.6: "llama", 4.0: "qwen2", 4.5: "qwen3"}
if behavior == MiniCPMVConfigBehavior.TEXT_EMBEDDINGS:
return get_vlm_text_embeddings_config("qwen2", self._orig_config, self.int_dtype, self.float_dtype)
return get_vlm_text_embeddings_config(
model_mapping[self._orig_config.version],
self._orig_config,
self.int_dtype,
self.float_dtype,
)

if behavior == MiniCPMVConfigBehavior.LANGUAGE:
return get_vlm_text_generation_config("qwen2", self._orig_config, self.int_dtype, self.float_dtype)
return get_vlm_text_generation_config(
model_mapping[self._orig_config.version],
self._orig_config,
self.int_dtype,
self.float_dtype,
)

if behavior == MiniCPMVConfigBehavior.VISION_EMBEDDINGS:
return self.__class__(
Expand Down
22 changes: 22 additions & 0 deletions tests/openvino/test_exporters_cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -635,6 +635,28 @@ class OVCLIExportTestCase(unittest.TestCase):
"resampler_model": {"int8": 6},
},
),
(
"image-text-to-text",
"minicpmv4",
"int4 --group-size 4 --ratio 0.8 --trust-remote-code",
{
"lm_model": {"int8": 12, "int4": 18},
"text_embeddings_model": {"int8": 1},
"vision_embeddings_model": {"int8": 14},
"resampler_model": {"int8": 6},
},
),
(
"image-text-to-text",
"minicpmv4_5",
"int4 --group-size 4 --ratio 0.8 --trust-remote-code",
{
"lm_model": {"int8": 12, "int4": 18},
"text_embeddings_model": {"int8": 1},
"vision_embeddings_model": {"int8": 14},
"resampler_model": {"int8": 6},
},
),
(
"image-text-to-text",
"internvl_chat",
Expand Down
44 changes: 44 additions & 0 deletions tests/openvino/test_quantization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1027,6 +1027,48 @@ class OVWeightCompressionTest(unittest.TestCase):
"resampler_model": {"int8": 6},
},
),
(
OVModelForVisualCausalLM,
"minicpmv4",
True,
dict(
bits=4,
group_size=16,
dataset="contextual",
ratio=0.8,
sensitivity_metric="mean_activation_magnitude",
num_samples=1,
processor=MODEL_NAMES["minicpmv"],
trust_remote_code=True,
),
{
"lm_model": {"int8": 8, "int4": 22},
"text_embeddings_model": {"int8": 1},
"vision_embeddings_model": {"int8": 26},
"resampler_model": {"int8": 6},
},
),
(
OVModelForVisualCausalLM,
"minicpmv4_5",
True,
dict(
bits=4,
group_size=16,
dataset="contextual",
ratio=0.8,
sensitivity_metric="mean_activation_magnitude",
num_samples=1,
processor=MODEL_NAMES["minicpmv"],
trust_remote_code=True,
),
{
"lm_model": {"int8": 8, "int4": 22},
"text_embeddings_model": {"int8": 1},
"vision_embeddings_model": {"int8": 26},
"resampler_model": {"int8": 6},
},
),
]

# filter models type depending on min max transformers version
Expand All @@ -1053,6 +1095,8 @@ class OVWeightCompressionTest(unittest.TestCase):
(OVModelForVisualCausalLM, "llava_next_video", False),
(OVModelForVisualCausalLM, "minicpmv", True),
(OVModelForVisualCausalLM, "qwen2_vl", False),
(OVModelForVisualCausalLM, "minicpmv4", False),
(OVModelForVisualCausalLM, "minicpmv4_5", False),
]

if is_transformers_version("<", "4.54.0"):
Expand Down
12 changes: 6 additions & 6 deletions tests/openvino/test_seq2seq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -497,7 +497,7 @@ class OVModelForVisualCausalLMIntegrationTest(unittest.TestCase):
if is_transformers_version(">", "4.49"):
SUPPORTED_ARCHITECTURES += ["gemma3", "smolvlm"]
if is_transformers_version(">=", "4.51"):
SUPPORTED_ARCHITECTURES += ["llama4"]
SUPPORTED_ARCHITECTURES += ["llama4", "minicpmv4", "minicpmv4_5"]
if is_transformers_version("<", "4.52"):
SUPPORTED_ARCHITECTURES += ["minicpmo"]

Expand All @@ -506,7 +506,7 @@ class OVModelForVisualCausalLMIntegrationTest(unittest.TestCase):
SUPPORTED_ARCHITECTURES = set(SUPPORTED_ARCHITECTURES) - {"llava-qwen2", "phi3_v", "phi4mm"}

TASK = "image-text-to-text"
REMOTE_CODE_MODELS = ["internvl_chat", "minicpmv", "minicpmo", "llava-qwen2", "phi3_v", "maira2", "phi4mm"]
REMOTE_CODE_MODELS = ["internvl_chat", "minicpmv", "minicpmv4", "minicpmv4_5", "minicpmo", "llava-qwen2", "phi3_v", "maira2", "phi4mm"]

IMAGE = Image.open(
requests.get(
Expand Down Expand Up @@ -611,7 +611,7 @@ def test_compare_to_transformers(self, model_arch):
self._check_device_and_request(ov_model, test_device, False)

# pytorch minicpmv and internvl_chat are not designed to be used via forward
if model_arch not in ["minicpmv", "minicpmo", "internvl_chat"]:
if model_arch not in ["minicpmv", "minicpmv4","minicpmv4_5","minicpmo", "internvl_chat"]:
set_seed(SEED)
ov_outputs = ov_model(**inputs)
set_seed(SEED)
Expand Down Expand Up @@ -670,7 +670,7 @@ def test_compare_to_transformers(self, model_arch):
transformers_outputs = transformers_outputs[1].sequences

# original minicpmv, internvl always skip input tokens in generation results, while transformers based approach provide them
if model_arch in ["minicpmv", "minicpmo", "internvl_chat"]:
if model_arch in ["minicpmv", "minicpmv4", "minicpmv4_5", "minicpmo", "internvl_chat"]:
ov_outputs = ov_outputs[:, inputs["input_ids"].shape[1] :]
self.assertTrue(
torch.equal(ov_outputs, transformers_outputs),
Expand All @@ -696,7 +696,7 @@ def test_compare_to_transformers(self, model_arch):
transformers_inputs = copy.deepcopy(inputs)
ov_outputs = ov_model.generate(**inputs, generation_config=gen_config)
# original minicpmv, internvl always skip input tokens in generation results, while transformers based approach provide them
if model_arch in ["minicpmv", "minicpmo", "internvl_chat"]:
if model_arch in ["minicpmv", "minicpmv4", "minicpmv4_5", "minicpmo", "internvl_chat"]:
ov_outputs = ov_outputs[:, inputs["input_ids"].shape[1] :]
with torch.no_grad():
transformers_outputs = transformers_model.generate(
Expand All @@ -714,7 +714,7 @@ def test_compare_to_transformers(self, model_arch):
transformers_inputs = copy.deepcopy(inputs)
ov_outputs = ov_model.generate(**inputs, generation_config=gen_config)
# original minicpmv, internvl always skip input tokens in generation results, while transformers based approach provide them
if model_arch in ["minicpmv", "minicpmo", "internvl_chat"]:
if model_arch in ["minicpmv", "minicpmv4", "minicpmv4_5", "minicpmo", "internvl_chat"]:
ov_outputs = ov_outputs[:, inputs["input_ids"].shape[1] :]
with torch.no_grad():
transformers_outputs = transformers_model.generate(
Expand Down
14 changes: 14 additions & 0 deletions tests/openvino/utils_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,8 @@
"minicpm": "katuni4ka/tiny-random-minicpm",
"minicpm3": "katuni4ka/tiny-random-minicpm3",
"minicpmv": "katuni4ka/tiny-random-minicpmv-2_6",
"minicpmv4": "snake7gun/minicpm-v-4-tiny",
"minicpmv4_5": "tiny-random/minicpm-v-4_5",
"minicpmo": "rkazants/tiny-random-MiniCPM-o-2_6",
"mistral": "echarlaix/tiny-random-mistral",
"mistral-nemo": "katuni4ka/tiny-random-mistral-nemo",
Expand Down Expand Up @@ -285,6 +287,18 @@
"vision_embeddings_model": 26,
"resampler_model": 6,
},
"minicpmv4": {
"lm_model": 30,
"text_embeddings_model": 1,
"vision_embeddings_model": 14,
"resampler_model": 6,
},
"minicpmv4_5": {
"lm_model": 30,
"text_embeddings_model": 1,
"vision_embeddings_model": 14,
"resampler_model": 6,
},
"llava_next_video": {
"lm_model": 30,
"text_embeddings_model": 1,
Expand Down