Chirag Jain
50896ec574
Make nvcc threads configurable via environment variable (#885)
|
před 9 měsíci | |
|---|---|---|
| .. | ||
| README.md | před 1 rokem | |
| interface.cpp | před 2 roky | |
| setup.py | před 9 měsíci | |
| xentropy_kernel.cu | před 2 roky | |
README.md
This CUDA extension implements optimized cross-entropy loss, adapted from Apex's Xentropy. We make it work for bfloat16 and support in-place backward to save memory.
It has only been tested on A100s.
cd csrc/xentropy && pip install .
As of 2023-09-15, this extension is no longer used in the FlashAttention repo. We've instead switched to a Triton-based implementation. See the CrossEntropyLoss module for more details.