[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:
Tiezhen WANG
2026-06-22 15:20:46 +08:00
committed by GitHub
co-authored by Claude mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 68567ef2df
commit d14e551a53
20 changed files with 10 additions and 3881 deletions
@@ -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