We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 0298bee commit ba55201Copy full SHA for ba55201
Dockerfile
@@ -41,7 +41,7 @@ RUN pip install -r /lightllm/requirements.txt --no-cache-dir --ignore-installed
41
RUN pip install --no-cache-dir nvidia-nccl-cu12==2.25.1 # for allreduce hang issues in multinode H100
42
43
RUN git clone https://github.com/Dao-AILab/flash-attention.git -b v2.7.4.post1
44
-RUN cd flash-attention/hopper && NVCC_THREADS=128 python setup.py install
+RUN cd flash-attention/hopper && NVCC_THREADS=16 python setup.py install
45
46
COPY . /lightllm
47
RUN pip install -e /lightllm --no-cache-dir
0 commit comments