Describe the bug
Under seq_len 2048, BS=8, heads=32, get_workspace_size will return negative value in get_workspace_size
To Reproduce
In function to compute workspace size, when seq_len =2048, maxBatchSize=8, num of heads=32, in the function below:
https://github.com/microsoft/DeepSpeed/blob/master/csrc/transformer/ds_transformer_cuda.cpp#L22
The value of workSpacesize will overflow and get a negative number
Expected behavior
workSpacesize and return value should use size_t to avoid overflow.
ds_report output
Please run ds_report to give us details about your setup.
Screenshots
If applicable, add screenshots to help explain your problem.
System info (please complete the following information):
- OS: [e.g. Ubuntu 18.04]
- GPU count and types [e.g. two machines with x8 A100s each]
- Interconnects (if applicable) [e.g., two machines connected with 100 Gbps IB]
- Python version
- Any other relevant info about your setup
Launcher context
Are you launching your experiment with the deepspeed launcher, MPI, or something else?
Docker context
Are you using a specific docker image that you can share?
Additional context
Add any other context about the problem here.
Describe the bug
Under seq_len 2048, BS=8, heads=32, get_workspace_size will return negative value in get_workspace_size
To Reproduce
In function to compute workspace size, when seq_len =2048, maxBatchSize=8, num of heads=32, in the function below:
https://github.com/microsoft/DeepSpeed/blob/master/csrc/transformer/ds_transformer_cuda.cpp#L22
The value of workSpacesize will overflow and get a negative number
Expected behavior
workSpacesize and return value should use size_t to avoid overflow.
ds_report output
Please run
ds_reportto give us details about your setup.Screenshots
If applicable, add screenshots to help explain your problem.
System info (please complete the following information):
Launcher context
Are you launching your experiment with the
deepspeedlauncher, MPI, or something else?Docker context
Are you using a specific docker image that you can share?
Additional context
Add any other context about the problem here.