-
## 🐛 Bug
After the installation is complete run
` llm -m Llama-2-7b-chat 'five names for a cute pet ferret'`
Error messages show:
`Error: Traceback (most recent call last): Traceback (most recen…
-
Current TensorViewToNumpy and NumpyToTensorViews only work on rank < 5 matrices.
Proposing to increase to add rank=5 support and add a `static_assert` so users will know about the implementation l…
-
## 🐛 Bug
I am trying to compile the example model `python3 build.py --hf-path togethercomputer/RedPajama-INCITE-Chat-3B-v1 --target webgpu --quantization q4f16_0` from [the docs](https://mlc.ai/mlc…
-
In NumPy (and some other libraries) arrays have a method to [`view`]( https://numpy.org/doc/stable/reference/generated/numpy.ndarray.view.html ) the data as another `dtype`. This is different from `as…
-
**Describe the bug**
`Series.mean` with `skipna=False` gives a result that is hard to understand
**Steps/Code to reproduce bug**
```
In [2]: s = cudf.Series([None, 0, 1, 1, None, 2, 3, 3, 4,…
-
**Describe the bug**
Casting an int column to decimal128 type goes through `from_arrow` machinery, which seems to not have support for `decimal128`.
**Steps/Code to reproduce bug**
PR needed to h…
-
**Describe the bug**
Conversion from string to `decimal128` types seem to be broken.
**Steps/Code to reproduce bug**
PR needed to have decimal128 python machinery: https://github.com/rapidsai/cud…
-
**Describe the bug**
A `cudaErrorIllegalAddress` error is triggered when using regular expressions and replace with some combinations of inputs and outputs with `*` and `?`. This error is a permanen…
-
**Describe the bug**
When reading in a parquet table containing datetime columns using `dask_cudf.read_parquet`, the datetime columns have mismatched precisions between the Dask object's meta and the…
-
## 🐛 Bug
When compiling with `python3 -m mlc_llm.build --hf-path meta-llama/Llama-2-7b-chat-hf --target webgpu --quantization q4f32_0` I get `assert not (is_reduction ^ is_inner_reduction)`.
## …