[Model] Remove MiniMaxText01, MiniMaxVL01, MiniMaxForCausalLM (#45993)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Claude
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
68567ef2df
commit
d14e551a53
@@ -810,29 +810,6 @@ VLM_TEST_SETTINGS = {
|
||||
hf_output_post_proc=model_utils.minicpmv_trunc_hf_output,
|
||||
patch_hf_runner=model_utils.minicpmv_26_patch_hf_runner,
|
||||
),
|
||||
"minimax_vl_01": VLMTestInfo(
|
||||
models=["MiniMaxAI/MiniMax-VL-01"],
|
||||
prompt_formatter=lambda img_prompt: f"<beginning_of_sentence>user: {img_prompt} assistant:<end_of_sentence>", # noqa: E501
|
||||
img_idx_to_prompt=lambda _: "<image>",
|
||||
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),
|
||||
max_model_len=8192,
|
||||
max_num_seqs=4,
|
||||
dtype="bfloat16",
|
||||
hf_output_post_proc=model_utils.minimax_vl_01_hf_output,
|
||||
patch_hf_runner=model_utils.minimax_vl_01_patch_hf_runner,
|
||||
auto_cls=AutoModelForImageTextToText,
|
||||
marks=[
|
||||
large_gpu_mark(min_gb=80),
|
||||
# TODO: [ROCm] Fix pickle issue with ROCm spawn and tp>1
|
||||
pytest.mark.skipif(
|
||||
current_platform.is_rocm(),
|
||||
reason=(
|
||||
"ROCm: Model too large for single GPU; "
|
||||
"multi-GPU blocked by HF _LazyConfigMapping pickle issue with spawn"
|
||||
),
|
||||
),
|
||||
],
|
||||
),
|
||||
"molmo": VLMTestInfo(
|
||||
models=["allenai/Molmo-7B-D-0924"],
|
||||
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),
|
||||
|
||||
@@ -245,13 +245,6 @@ def minicpmv_trunc_hf_output(hf_output: RunnerOutput, model: str) -> RunnerOutpu
|
||||
return output_ids, output_str, out_logprobs
|
||||
|
||||
|
||||
def minimax_vl_01_hf_output(hf_output: RunnerOutput, model: str) -> RunnerOutput:
|
||||
output_ids, output_str, out_logprobs = hf_output
|
||||
if output_str.endswith("<end_of_sentence>"):
|
||||
output_str = output_str.split("<end_of_sentence>")[0]
|
||||
return output_ids, output_str, out_logprobs
|
||||
|
||||
|
||||
def ultravox_trunc_hf_output(hf_output: RunnerOutput, model: str) -> RunnerOutput:
|
||||
output_ids, output_str, out_logprobs = hf_output
|
||||
|
||||
@@ -1023,17 +1016,6 @@ def minicpmv_26_patch_hf_runner(hf_model: HfRunner) -> HfRunner:
|
||||
return hf_model
|
||||
|
||||
|
||||
def minimax_vl_01_patch_hf_runner(hf_model: HfRunner) -> HfRunner:
|
||||
orig_generate = hf_model.model.generate
|
||||
|
||||
def _generate(self, *args, image_sizes=None, **kwargs):
|
||||
return orig_generate(*args, decode_text=False, **kwargs)
|
||||
|
||||
hf_model.model.generate = types.MethodType(_generate, hf_model.model)
|
||||
|
||||
return hf_model
|
||||
|
||||
|
||||
def molmo_patch_hf_runner(hf_model: HfRunner) -> HfRunner:
|
||||
"""Patches and returns an instance of the HfRunner to use for Molmo."""
|
||||
hf_processor = hf_model.processor
|
||||
|
||||
@@ -1,113 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
from PIL import Image
|
||||
|
||||
from vllm.multimodal import MULTIMODAL_REGISTRY
|
||||
from vllm.multimodal.parse import ImageSize
|
||||
from vllm.multimodal.processing import BaseMultiModalProcessor
|
||||
|
||||
from ....conftest import ImageTestAssets
|
||||
from ...utils import build_model_context
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model_id", ["MiniMaxAI/MiniMax-VL-01"])
|
||||
@pytest.mark.parametrize("num_imgs", [1, 2])
|
||||
def test_processor_override(
|
||||
image_assets: ImageTestAssets,
|
||||
model_id: str,
|
||||
num_imgs: int,
|
||||
):
|
||||
ctx = build_model_context(
|
||||
model_id,
|
||||
mm_processor_kwargs=None,
|
||||
limit_mm_per_prompt={"image": num_imgs},
|
||||
)
|
||||
processor = MULTIMODAL_REGISTRY.create_processor(ctx.model_config)
|
||||
prompt = "<image>" * num_imgs
|
||||
image = Image.new("RGB", size=(364, 364))
|
||||
mm_data = {"image": [image] * num_imgs}
|
||||
|
||||
processed_inputs = processor(
|
||||
prompt,
|
||||
mm_items=processor.info.parse_mm_data(mm_data),
|
||||
hf_processor_mm_kwargs={},
|
||||
)
|
||||
image_placeholders = processed_inputs["mm_placeholders"]["image"]
|
||||
|
||||
assert len(image_placeholders) == num_imgs
|
||||
|
||||
|
||||
def _validate_image_prompt_replacements_one(
|
||||
processor: BaseMultiModalProcessor,
|
||||
num_imgs: int,
|
||||
failed_size_excs: list[tuple[ImageSize, Exception]],
|
||||
image_size: ImageSize,
|
||||
) -> None:
|
||||
prompt = "<image>" * num_imgs
|
||||
image = Image.new("RGB", size=image_size)
|
||||
mm_data = {"image": [image] * num_imgs}
|
||||
|
||||
try:
|
||||
processed_inputs = processor(
|
||||
prompt,
|
||||
mm_items=processor.info.parse_mm_data(mm_data),
|
||||
hf_processor_mm_kwargs={},
|
||||
)
|
||||
|
||||
image_placeholders = processed_inputs["mm_placeholders"]["image"]
|
||||
assert len(image_placeholders) == num_imgs
|
||||
|
||||
except Exception as exc:
|
||||
failed_size_excs.append((image_size, exc))
|
||||
|
||||
|
||||
def _test_image_prompt_replacements(
|
||||
processor,
|
||||
*,
|
||||
num_imgs: int,
|
||||
image_sizes: list[ImageSize],
|
||||
) -> None:
|
||||
failed_size_excs = list[tuple[ImageSize, Exception]]()
|
||||
|
||||
for size in image_sizes:
|
||||
_validate_image_prompt_replacements_one(
|
||||
processor, num_imgs, failed_size_excs, size
|
||||
)
|
||||
|
||||
if failed_size_excs:
|
||||
msg = "Found failing image sizes:" + "\n========\n".join(
|
||||
f"[{size}]\n{exc}" for size, exc in failed_size_excs
|
||||
)
|
||||
raise AssertionError(msg)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model_id", ["MiniMaxAI/MiniMax-VL-01"])
|
||||
@pytest.mark.parametrize("num_imgs", [1, 2])
|
||||
def test_processor_prompt_replacements_regression(model_id, num_imgs):
|
||||
ctx = build_model_context(
|
||||
model_id,
|
||||
mm_processor_kwargs=None,
|
||||
limit_mm_per_prompt={"image": num_imgs},
|
||||
)
|
||||
processor = MULTIMODAL_REGISTRY.create_processor(ctx.model_config)
|
||||
|
||||
image_ratios = [
|
||||
(171, 152),
|
||||
(184, 161),
|
||||
(198, 176),
|
||||
(333, 296),
|
||||
(369, 328),
|
||||
(488, 183),
|
||||
(2560, 1669),
|
||||
]
|
||||
image_sizes = [
|
||||
size for w, h in image_ratios for size in [ImageSize(w, h), ImageSize(h, w)]
|
||||
]
|
||||
|
||||
_test_image_prompt_replacements(
|
||||
processor,
|
||||
num_imgs=num_imgs,
|
||||
image_sizes=image_sizes,
|
||||
)
|
||||
@@ -421,15 +421,6 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
|
||||
},
|
||||
trust_remote_code=True,
|
||||
),
|
||||
"MiniMaxForCausalLM": _HfExamplesInfo("MiniMaxAI/MiniMax-Text-01-hf"),
|
||||
"MiniMaxText01ForCausalLM": _HfExamplesInfo(
|
||||
"MiniMaxAI/MiniMax-Text-01",
|
||||
trust_remote_code=True,
|
||||
revision="a59aa9cbc53b9fb8742ca4e9e1531b9802b6fdc3",
|
||||
),
|
||||
"MiniMaxM1ForCausalLM": _HfExamplesInfo(
|
||||
"MiniMaxAI/MiniMax-M1-40k", trust_remote_code=True
|
||||
),
|
||||
"MiniMaxM2ForCausalLM": _HfExamplesInfo(
|
||||
"MiniMaxAI/MiniMax-M2",
|
||||
trust_remote_code=True,
|
||||
@@ -1113,10 +1104,6 @@ _MULTIMODAL_EXAMPLE_MODELS = {
|
||||
"openbmb/MiniCPM-V-4_6",
|
||||
min_transformers_version="5.7.0",
|
||||
),
|
||||
"MiniMaxVL01ForConditionalGeneration": _HfExamplesInfo(
|
||||
"MiniMaxAI/MiniMax-VL-01",
|
||||
trust_remote_code=True,
|
||||
),
|
||||
"MiniMaxM3SparseForConditionalGeneration": _HfExamplesInfo(
|
||||
"MiniMaxAI/MiniMax-M3",
|
||||
trust_remote_code=True,
|
||||
|
||||
@@ -98,11 +98,6 @@ def can_initialize(
|
||||
vllm_config.validate_block_size()
|
||||
return scheduler_kv_cache_config
|
||||
|
||||
if model_arch == "MiniMaxVL01ForConditionalGeneration":
|
||||
pytest.skip(
|
||||
"pickle error when loading `transformers.models.auto.CONFIG_MAPPING`"
|
||||
)
|
||||
|
||||
if model_arch == "MoonshotKimiaForCausalLM":
|
||||
pytest.skip(
|
||||
"Kimi-Audio requires SpeechToTextConfig "
|
||||
|
||||
Reference in New Issue
Block a user