DeepSpeed
644fea44
- fixing some bug in softmax kernel for batch_size>1
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Hide Minimap (CTRL+M)
Commit
2 years ago
fixing some bug in softmax kernel for batch_size>1
References
#2083 - Add Inference support for running the BigScience-BLOOM Architecture
Author
Reza Yazdani
Parents
1cef202d
Files
3
csrc/transformer/inference/csrc
pt_binding.cpp
softmax.cu
deepspeed/ops/transformer/inference
transformer_inference.py
Loading