@@ -1,6 +1,6 @@
|
||||
# Testing mixed int8 quantization
|
||||
|
||||

|
||||

|
||||
|
||||
The following is the recipe on how to effectively debug `bitsandbytes` integration on Hugging Face `transformers`.
|
||||
|
||||
@@ -89,11 +89,11 @@ Here is an example of a badly configured CUDA installation:
|
||||
|
||||
`nvcc --version` gives:
|
||||
|
||||

|
||||

|
||||
|
||||
which means that the detected CUDA version is 11.3 but `bitsandbytes` outputs:
|
||||
|
||||

|
||||

|
||||
|
||||
First check:
|
||||
|
||||
@@ -115,6 +115,6 @@ ls -l $LD_LIBRARY_PATH/libcudart.so
|
||||
|
||||
and you can see
|
||||
|
||||

|
||||

|
||||
|
||||
If you see that the file is linked to the wrong CUDA version (here 10.2), find the correct location for `libcudart.so` (`find --name libcudart.so`) and replace the environment variable `LD_LIBRARY_PATH` with the one containing the correct `libcudart.so` file.
|
||||
Reference in New Issue
Block a user