Error in importing from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel in GoogleCollab

[ankitsrivastava637]

ERROR: Could not find a version that satisfies the requirement mamba_ssm.models.mixer_seq_simple (from versions: none)
ERROR: No matching distribution found for mamba_ssm.models.mixer_seq_simple
ERROR: Could not find a version that satisfies the requirement causal_conv1d_cuda (from versions: none)
ERROR: No matching distribution found for causal_conv1d_cuda

ImportError Traceback (most recent call last)
in <cell line: 5>()
3 get_ipython().system('pip install mamba_ssm.models.mixer_seq_simple')
4 get_ipython().system('pip install causal_conv1d_cuda')
----> 5 from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
6
7 device = "cuda"

3 frames
/usr/local/lib/python3.10/dist-packages/causal_conv1d/causal_conv1d_interface.py in
5
6
----> 7 import causal_conv1d_cuda
8
9

ImportError: /usr/local/lib/python3.10/dist-packages/causal_conv1d_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops10zeros_like4callERKNS_6TensorEN3c108optionalINS5_10ScalarTypeEEENS6_INS5_6LayoutEEENS6_INS5_6DeviceEEENS6_IbEENS6_INS5_12MemoryFormatEEE

[unnir]

the same error for me on google colab

[Rohith04MVK]

Could you try installing causal-conv1d manually and not from the requirements using pip install causal-conv1d ?

[TinChung41]

same error on Colab in May