mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-22 15:32:08 +00:00
Download kernels in install-cuda
target
This commit is contained in:
parent
141c97e34e
commit
c6dd5d0e22
@ -39,6 +39,7 @@ install: install-cuda
|
|||||||
install-cuda: install-server install-flash-attention-v2-cuda install-flash-attention
|
install-cuda: install-server install-flash-attention-v2-cuda install-flash-attention
|
||||||
uv pip install -e ".[attention,bnb,marlin,moe]"
|
uv pip install -e ".[attention,bnb,marlin,moe]"
|
||||||
uv pip install nvidia-nccl-cu12==2.22.3
|
uv pip install nvidia-nccl-cu12==2.22.3
|
||||||
|
kernels download .
|
||||||
|
|
||||||
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
|
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user