biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Refactoring of MiniCPM-V and add MiniCPM-o-2.6 support for vLLM (#12069)

Browse Source 
Signed-off-by: hzh <hezhihui_thu@163.com>
Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Signed-off-by: shaochangxu.scx <shaochangxu.scx@antgroup.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>
Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Oleg Mosalov <oleg@krai.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: Yida Wu <yidawu@alumni.cmu.edu>
Signed-off-by: Chenguang Li <757486878@qq.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Shanshan Shen <467638484@qq.com>
Signed-off-by: elijah <f1renze.142857@gmail.com>
Signed-off-by: Yikun <yikunkero@gmail.com>
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Co-authored-by: shaochangxu <85155497+shaochangxu@users.noreply.github.com>
Co-authored-by: shaochangxu.scx <shaochangxu.scx@antgroup.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: sixgod <evethwillbeok@outlook.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Rafael Vasquez <rafvasq21@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Akshat Tripathi <Akshat.tripathi6568@gmail.com>
Co-authored-by: Oleg Mosalov <oleg@krai.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Avshalom Manevich <12231371+avshalomman@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Yangcheng Li <liyangcheng.lyc@alibaba-inc.com>
Co-authored-by: Siyuan Li <94890248+liaoyanqing666@users.noreply.github.com>
Co-authored-by: Concurrensee <yida.wu@amd.com>
Co-authored-by: Chenguang Li <757486878@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Alex Brooks <alex.brooks@ibm.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: elijah <30852919+e1ijah1@users.noreply.github.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Steve Luo <36296769+SunflowerAries@users.noreply.github.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Konrad Zawora <kzawora@habana.ai>
Co-authored-by: TJian <tunjian1996@gmail.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: maang-h <55082429+maang-h@users.noreply.github.com>
Co-authored-by: Elfie Guo <164945471+elfiegg@users.noreply.github.com>
Co-authored-by: Rui Qiao <161574667+ruisearch42@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Alphi
2025-01-29 17:24:59 +08:00
committed by GitHub
parent 036ca94c25
commit d93bf4da85
15 changed files with 1627 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tests/models/decoder_only/vision_language/test_models.py
View File

@@ -350,6 +350,20 @@ VLM_TEST_SETTINGS = {
postprocess_inputs=model_utils.wrap_inputs_post_processor,
hf_output_post_proc=model_utils.minicpmv_trunc_hf_output,
),
"minicpmo_26": VLMTestInfo(
models=["openbmb/MiniCPM-o-2_6"],
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),
prompt_formatter=lambda img_prompt: f"<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n{img_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n", # noqa: E501
img_idx_to_prompt=lambda idx: "(<image>./</image>)\n",
max_model_len=4096,
max_num_seqs=2,
get_stop_token_ids=lambda tok: tok.convert_tokens_to_ids(['<|im_end|>', '<|endoftext|>']), # noqa: E501
postprocess_inputs=model_utils.ignore_inputs_post_processor(
"image_sizes"
),
hf_output_post_proc=model_utils.minicpmv_trunc_hf_output,
patch_hf_runner=model_utils.minicpmo_patch_hf_runner
),
"minicpmv_26": VLMTestInfo(
models=["openbmb/MiniCPM-V-2_6"],
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),

11
tests/models/decoder_only/vision_language/vlm_utils/model_utils.py
View File

@@ -497,6 +497,17 @@ def mantis_patch_hf_runner(hf_model: HfRunner) -> HfRunner:
return hf_model
def minicpmo_patch_hf_runner(hf_model: HfRunner) -> HfRunner:
orig_generate = hf_model.model.generate
def _generate(self, *args, **kwargs):
return orig_generate(*args, decode_text=False, **kwargs)
hf_model.model.generate = types.MethodType(_generate, hf_model.model)
return hf_model
def _generate_greedy_logprobs_limit(
self,
prompts: List[str],

2
tests/models/multimodal/processing/test_common.py
View File

@@ -152,6 +152,8 @@ def _test_processing_correctness(
"llava-hf/llava-onevision-qwen2-0.5b-ov-hf",
"TIGER-Lab/Mantis-8B-siglip-llama3",
"mistral-community/pixtral-12b",
"openbmb/MiniCPM-o-2_6",
"openbmb/MiniCPM-V-2_6",
"Qwen/Qwen-VL-Chat",
"Qwen/Qwen2-VL-2B-Instruct",
"Qwen/Qwen2-Audio-7B-Instruct",

4
tests/models/registry.py
View File

@@ -245,7 +245,9 @@ _MULTIMODAL_EXAMPLE_MODELS = {
"LlavaOnevisionForConditionalGeneration": _HfExamplesInfo("llava-hf/llava-onevision-qwen2-0.5b-ov-hf"), # noqa: E501
"MantisForConditionalGeneration": _HfExamplesInfo("TIGER-Lab/Mantis-8B-siglip-llama3", # noqa: E501
hf_overrides={"architectures": ["MantisForConditionalGeneration"]}), # noqa: E501
"MiniCPMV": _HfExamplesInfo("openbmb/MiniCPM-Llama3-V-2_5",
"MiniCPMO": _HfExamplesInfo("openbmb/MiniCPM-o-2_6",
trust_remote_code=True),
"MiniCPMV": _HfExamplesInfo("openbmb/MiniCPM-V-2_6",
trust_remote_code=True),
"MolmoForCausalLM": _HfExamplesInfo("allenai/Molmo-7B-D-0924",
trust_remote_code=True),