Jeffery

I also have the same problem. Did you find any solution to solve it?

Same error ``` [ FAILED ] LmInferenceTest.test_lm_decode [ RUN ] LmInferenceTest.test_lm_score_may_fail_numerically_for_external_meliad [ FAILED ] LmInferenceTest.test_lm_score_may_fail_numerically_for_external_meliad ====================================================================== ERROR: test_lm_score_may_fail_numerically_for_external_meliad (__main__.LmInferenceTest) ---------------------------------------------------------------------- Traceback (most recent call last): File "geo/lm_inference_test.py", line 77, in...

Can you please provide the version of tensor-RT used for the model?

`xformers==0.0.27` requires `torch==2.3.1` as well, I change to `torch==2.3.1+cu118` and installed the environment successfully, but the corresponding `flash_attn` would require `libcudart.so.12` from cuda 12+, I am not sure how to...

my problem is solved by changing the python version to 3.10 and with underlying packages: ```sh $ conda list # packages in environment at miniconda3/envs/axo: # # Name Version Build...

I changed to `python==3.10` and everything works