BetterTransformer requires transformers<4.49 but found 4.51.3

[bannert1337]

System Info

root@harbor:~/infinity# uv venv --python 3.12 --seed
Using CPython 3.12.11
Creating virtual environment with seed packages at: .venv
 + pip==25.1.1
Activate with: source .venv/bin/activate
root@harbor:~/infinity# source .venv/bin/activate
(infinity) root@harbor:~/infinity# uv pip install infinity-emb[all]
Resolved 112 packages in 564ms
Prepared 14 packages in 16.03s
Installed 112 packages in 379ms
 + accelerate==1.7.0
 + aiohappyeyeballs==2.6.1
 + aiohttp==3.12.12
 + aiosignal==1.3.2
 + annotated-types==0.7.0
 + anyio==4.9.0
 + attrs==25.3.0
 + backoff==2.2.1
 + certifi==2025.4.26
 + cffi==1.17.1
 + charset-normalizer==3.4.2
 + click==8.2.1
 + coloredlogs==15.0.1
 + colpali-engine==0.3.10
 + ctranslate2==4.6.0
 + datasets==3.6.0
 + dill==0.3.8
 + diskcache==5.6.3
 + distro==1.9.0
 + einops==0.8.1
 + fastapi==0.115.12
 + filelock==3.18.0
 + flatbuffers==25.2.10
 + frozenlist==1.7.0
 + fsspec==2025.3.0
 + h11==0.16.0
 + hf-transfer==0.1.9
 + hf-xet==1.1.3
 + httptools==0.6.4
 + huggingface-hub==0.33.0
 + humanfriendly==10.0
 + idna==3.10
 + infinity-emb==0.0.76
 + jinja2==3.1.6
 + joblib==1.5.1
 + markdown-it-py==3.0.0
 + markupsafe==3.0.2
 + mdurl==0.1.2
 + mpmath==1.3.0
 + multidict==6.4.4
 + multiprocess==0.70.16
 + networkx==3.5
 + numpy==1.26.4
 + nvidia-cublas-cu12==12.4.5.8
 + nvidia-cuda-cupti-cu12==12.4.127
 + nvidia-cuda-nvrtc-cu12==12.4.127
 + nvidia-cuda-runtime-cu12==12.4.127
 + nvidia-cudnn-cu12==9.1.0.70
 + nvidia-cufft-cu12==11.2.1.3
 + nvidia-curand-cu12==10.3.5.147
 + nvidia-cusolver-cu12==11.6.1.9
 + nvidia-cusparse-cu12==12.3.1.170
 + nvidia-cusparselt-cu12==0.6.2
 + nvidia-nccl-cu12==2.21.5
 + nvidia-nvjitlink-cu12==12.4.127
 + nvidia-nvtx-cu12==12.4.127
 + onnx==1.18.0
 + onnxruntime==1.22.0
 + optimum==1.25.3
 + orjson==3.10.18
 + packaging==25.0
 + pandas==2.3.0
 + peft==0.15.2
 + pillow==11.2.1
 + posthog==4.8.0
 + prometheus-client==0.22.1
 + prometheus-fastapi-instrumentator==7.1.0
 + propcache==0.3.2
 + protobuf==6.31.1
 + psutil==7.0.0
 + pyarrow==20.0.0
 + pycparser==2.22
 + pydantic==2.11.5
 + pydantic-core==2.33.2
 + pygments==2.19.1
 + python-dateutil==2.9.0.post0
 + python-dotenv==1.1.0
 + pytz==2025.2
 + pyyaml==6.0.2
 + regex==2024.11.6
 + requests==2.32.4
 + rich==13.9.4
 + safetensors==0.5.3
 + scikit-learn==1.7.0
 + scipy==1.15.3
 + sentence-transformers==3.4.1
 + setuptools==80.9.0
 + shellingham==1.5.4
 + six==1.17.0
 + sniffio==1.3.1
 + soundfile==0.12.1
 + starlette==0.46.2
 + sympy==1.13.1
 + threadpoolctl==3.6.0
 + timm==1.0.15
 + tokenizers==0.21.1
 + torch==2.6.0
 + torchvision==0.21.0
 + tqdm==4.67.1
 + transformers==4.51.3
 + triton==3.2.0
 + typer==0.12.5
 + typing-extensions==4.14.0
 + typing-inspection==0.4.1
 + tzdata==2025.2
 + urllib3==2.4.0
 + uvicorn==0.32.1
 + uvloop==0.21.0
 + watchfiles==1.0.5
 + websockets==15.0.1
 + xxhash==3.5.0
 + yarl==1.20.1
(infinity) root@harbor:~/infinity# infinity_emb v2 --engine torch --no-bettertransformer --model-id "Qwen/Qwen3-Embedding-0.6B" --model-id "Qwen/Qwen3-Reranker-0.6B" --port 7997
INFO     2025-06-12 15:41:57,697 datasets INFO: PyTorch version 2.6.0 available.                                                                                                                                                config.py:54
Traceback (most recent call last):
  File "/root/infinity/.venv/bin/infinity_emb", line 4, in <module>
    from infinity_emb.cli import cli
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/__init__.py", line 27, in <module>
    from infinity_emb.engine import AsyncEmbeddingEngine, AsyncEngineArray  # noqa: E402
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/engine.py", line 11, in <module>
    from infinity_emb.inference import (
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/inference/__init__.py", line 4, in <module>
    from infinity_emb.inference.batch_handler import BatchHandler
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/inference/batch_handler.py", line 39, in <module>
    from infinity_emb.transformer.utils import get_lengths_with_tokenize
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/utils.py", line 9, in <module>
    from infinity_emb.transformer.classifier.torch import SentenceClassifier
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/classifier/torch.py", line 8, in <module>
    from infinity_emb.transformer.acceleration import (
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/acceleration.py", line 11, in <module>
    from optimum.bettertransformer import (  # type: ignore[import-untyped]
  File "/root/infinity/.venv/lib/python3.12/site-packages/optimum/bettertransformer/__init__.py", line 20, in <module>
    raise RuntimeError(
RuntimeError: BetterTransformer requires transformers<4.49 but found 4.51.3. `optimum.bettertransformer` is deprecated and will be removed in optimum v2.0.
(infinity) root@harbor:~/infinity# infinity_emb v2 --help
INFO     2025-06-12 15:42:39,698 datasets INFO: PyTorch version 2.6.0 available.                                                                                                                                                config.py:54
Traceback (most recent call last):
  File "/root/infinity/.venv/bin/infinity_emb", line 4, in <module>
    from infinity_emb.cli import cli
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/__init__.py", line 27, in <module>
    from infinity_emb.engine import AsyncEmbeddingEngine, AsyncEngineArray  # noqa: E402
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/engine.py", line 11, in <module>
    from infinity_emb.inference import (
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/inference/__init__.py", line 4, in <module>
    from infinity_emb.inference.batch_handler import BatchHandler
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/inference/batch_handler.py", line 39, in <module>
    from infinity_emb.transformer.utils import get_lengths_with_tokenize
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/utils.py", line 9, in <module>
    from infinity_emb.transformer.classifier.torch import SentenceClassifier
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/classifier/torch.py", line 8, in <module>
    from infinity_emb.transformer.acceleration import (
  File "/root/infinity/.venv/lib/python3.12/site-packages/infinity_emb/transformer/acceleration.py", line 11, in <module>
    from optimum.bettertransformer import (  # type: ignore[import-untyped]
  File "/root/infinity/.venv/lib/python3.12/site-packages/optimum/bettertransformer/__init__.py", line 20, in <module>
    raise RuntimeError(
RuntimeError: BetterTransformer requires transformers<4.49 but found 4.51.3. `optimum.bettertransformer` is deprecated and will be removed in optimum v2.0.

Information

• Docker + cli
• pip + cli
• pip + usage of Python interface

Tasks

• An officially supported CLI command
• My own modifications

Reproduction

1. Install infinity-emb[all]
2. Run Qwen3-Embedding or Qwen3-Reranker

[Culturenotes]

(lazyllm) (base) l@l-Default-string:/media/l/D/Tutorial-main/Tutorial-main/rag/courseware_codes/chapter18$ infinity_emb v2 --engine torch --no-bettertransformer --model-id "Qwen/Qwen3-Embedding-0.6B" --model-id "Qwen/Qwen3-Reranker-0.6B" --port 7997
[2025-06-18 18:02:23,071] [INFO] [real_accelerator.py:254:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2025-06-18 18:02:25,749] [INFO] [logging.py:107:log_dist] [Rank -1] [TorchCheckpointEngine] Initialized with serialization = False
INFO 2025-06-18 18:02:25,838 datasets INFO: PyTorch version 2.6.0 available. config.py:54
Traceback (most recent call last):
File "/media/l/D/miniconda3/envs/lazyllm/bin/infinity_emb", line 5, in
from infinity_emb.cli import cli
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/init.py", line 27, in
from infinity_emb.engine import AsyncEmbeddingEngine, AsyncEngineArray # noqa: E402
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/engine.py", line 11, in
from infinity_emb.inference import (
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/inference/init.py", line 4, in
from infinity_emb.inference.batch_handler import BatchHandler
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/inference/batch_handler.py", line 39, in
from infinity_emb.transformer.utils import get_lengths_with_tokenize
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/transformer/utils.py", line 9, in
from infinity_emb.transformer.classifier.torch import SentenceClassifier
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/transformer/classifier/torch.py", line 8, in
from infinity_emb.transformer.acceleration import (
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/infinity_emb/transformer/acceleration.py", line 11, in
from optimum.bettertransformer import ( # type: ignore[import-untyped]
File "/media/l/D/miniconda3/envs/lazyllm/lib/python3.11/site-packages/optimum/bettertransformer/init.py", line 20, in
raise RuntimeError(
RuntimeError: BetterTransformer requires transformers<4.49 but found 4.51.3. optimum.bettertransformer is deprecated and will be removed in optimum v2.0.

I reinstall infinity_emb[all] and run the command, but still report an error

[wirthual]

Hi,
can you try this branch? #600

This should fix the problem by adding a version check.

[Greatz08]

pip install --upgrade "transformers<4.49" , use this command to fix that issue @Culturenotes