diff --git a/conda/environments/all_cuda-128_arch-aarch64.yaml b/conda/environments/all_cuda-128_arch-aarch64.yaml index c73a3bd68..a7a683f06 100644 --- a/conda/environments/all_cuda-128_arch-aarch64.yaml +++ b/conda/environments/all_cuda-128_arch-aarch64.yaml @@ -34,7 +34,7 @@ dependencies: - cuda-version=12.8 - cudf=25.02 - cuml=25.02.* -- cupy +- cupy<13.4 - cxx-compiler - cython=3.0 - datacompy=0.10 diff --git a/conda/environments/all_cuda-128_arch-x86_64.yaml b/conda/environments/all_cuda-128_arch-x86_64.yaml index 7d7ed2a88..710adad31 100644 --- a/conda/environments/all_cuda-128_arch-x86_64.yaml +++ b/conda/environments/all_cuda-128_arch-x86_64.yaml @@ -34,7 +34,7 @@ dependencies: - cuda-version=12.8 - cudf=25.02 - cuml=25.02.* -- cupy +- cupy<13.4 - cxx-compiler - cython=3.0 - datacompy=0.10 diff --git a/conda/environments/dev_cuda-128_arch-aarch64.yaml b/conda/environments/dev_cuda-128_arch-aarch64.yaml index 12dffdd28..f643adc34 100644 --- a/conda/environments/dev_cuda-128_arch-aarch64.yaml +++ b/conda/environments/dev_cuda-128_arch-aarch64.yaml @@ -27,7 +27,7 @@ dependencies: - cuda-sanitizer-api - cuda-version=12.8 - cudf=25.02 -- cupy +- cupy<13.4 - cxx-compiler - cython=3.0 - datacompy=0.10 diff --git a/conda/environments/dev_cuda-128_arch-x86_64.yaml b/conda/environments/dev_cuda-128_arch-x86_64.yaml index 0e1b07f83..854c3c767 100644 --- a/conda/environments/dev_cuda-128_arch-x86_64.yaml +++ b/conda/environments/dev_cuda-128_arch-x86_64.yaml @@ -27,7 +27,7 @@ dependencies: - cuda-sanitizer-api - cuda-version=12.8 - cudf=25.02 -- cupy +- cupy<13.4 - cxx-compiler - cython=3.0 - datacompy=0.10 diff --git a/conda/environments/examples_cuda-128_arch-aarch64.yaml b/conda/environments/examples_cuda-128_arch-aarch64.yaml index a80ac38ed..5c472ba8f 100644 --- a/conda/environments/examples_cuda-128_arch-aarch64.yaml +++ b/conda/environments/examples_cuda-128_arch-aarch64.yaml @@ -17,7 +17,7 @@ dependencies: - click>=8 - cudf=25.02 - cuml=25.02.* -- cupy +- cupy<13.4 - datacompy=0.10 - dill=0.3.7 - docker-py=5.0 diff --git a/conda/environments/examples_cuda-128_arch-x86_64.yaml b/conda/environments/examples_cuda-128_arch-x86_64.yaml index 2b145b9cd..b222bb64b 100644 --- a/conda/environments/examples_cuda-128_arch-x86_64.yaml +++ b/conda/environments/examples_cuda-128_arch-x86_64.yaml @@ -17,7 +17,7 @@ dependencies: - click>=8 - cudf=25.02 - cuml=25.02.* -- cupy +- cupy<13.4 - datacompy=0.10 - dill=0.3.7 - docker-py=5.0 diff --git a/conda/environments/runtime_cuda-128_arch-aarch64.yaml b/conda/environments/runtime_cuda-128_arch-aarch64.yaml index d315c27a1..d670efbf7 100644 --- a/conda/environments/runtime_cuda-128_arch-aarch64.yaml +++ b/conda/environments/runtime_cuda-128_arch-aarch64.yaml @@ -17,7 +17,7 @@ dependencies: - cuda-nvtx=12.8 - cuda-version=12.8 - cudf=25.02 -- cupy +- cupy<13.4 - datacompy=0.10 - dill=0.3.7 - docker-py=5.0 diff --git a/conda/environments/runtime_cuda-128_arch-x86_64.yaml b/conda/environments/runtime_cuda-128_arch-x86_64.yaml index 531a2a9c3..96c994f13 100644 --- a/conda/environments/runtime_cuda-128_arch-x86_64.yaml +++ b/conda/environments/runtime_cuda-128_arch-x86_64.yaml @@ -17,7 +17,7 @@ dependencies: - cuda-nvtx=12.8 - cuda-version=12.8 - cudf=25.02 -- cupy +- cupy<13.4 - datacompy=0.10 - dill=0.3.7 - docker-py=5.0 diff --git a/dependencies.yaml b/dependencies.yaml index f99528222..6d88cd395 100644 --- a/dependencies.yaml +++ b/dependencies.yaml @@ -384,7 +384,7 @@ dependencies: - click>=8 # - cuda-version=12.8 ## - *cudf - - cupy # Version determined from cudf + - cupy<13.4 # Version determined from cudf - datacompy=0.10 - dill=0.3.7 - docker-py=5.0 diff --git a/docs/source/developer_guide/guides/2_real_world_phishing.md b/docs/source/developer_guide/guides/2_real_world_phishing.md index bbe7f0ae5..5012c97e2 100644 --- a/docs/source/developer_guide/guides/2_real_world_phishing.md +++ b/docs/source/developer_guide/guides/2_real_world_phishing.md @@ -413,7 +413,7 @@ else: pipeline.add_stage(RecipientFeaturesStage(config)) ``` -To tokenize the input data we will use Morpheus' `PreprocessNLPStage`. This stage uses the [cuDF subword tokenizer](https://docs.rapids.ai/api/cudf/legacy/user_guide/api_docs/subword_tokenize/#subwordtokenizer) to transform strings into a tensor of numbers to be fed into the neural network model. Rather than split the string by characters or whitespaces, we split them into meaningful subwords based upon the occurrence of the subwords in a large training corpus. You can find more details here: [https://arxiv.org/abs/1810.04805v2](https://arxiv.org/abs/1810.04805v2). All we need to know for now is that the text will be converted to subword token ids based on the vocabulary file that we provide (`vocab_hash_file=vocab file`). +To tokenize the input data we will use Morpheus' `PreprocessNLPStage`. This stage uses the [cuDF subword tokenizer](https://docs.rapids.ai/api/cudf/stable/pylibcudf/api_docs/nvtext/subword_tokenize/) to transform strings into a tensor of numbers to be fed into the neural network model. Rather than split the string by characters or whitespaces, we split them into meaningful subwords based upon the occurrence of the subwords in a large training corpus. You can find more details here: [https://arxiv.org/abs/1810.04805v2](https://arxiv.org/abs/1810.04805v2). All we need to know for now is that the text will be converted to subword token ids based on the vocabulary file that we provide (`vocab_hash_file=vocab file`). Let's go ahead and instantiate our `PreprocessNLPStage` and add it to the pipeline: