huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make moe-kernels and marlin-kernels mandatory in CUDA installs

Browse Source
This commit is contained in:
Daniël de Kok 2024-10-10 08:28:55 +00:00
parent 43f39f6894
commit f30e2c7320
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/Makefile
View File

@ -31,7 +31,7 @@ install: install-cuda
echo "Installed server" echo "Installed server"
install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention install-fbgemm install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention install-fbgemm
pip install -e ".[bnb]" pip install -e ".[bnb,marlin,moe]"
pip install nvidia-nccl-cu12==2.22.3 pip install nvidia-nccl-cu12==2.22.3
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm