Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
text-generation-inference
Commits
f58eb70e
"...text-generation-inference.git" did not exist on "169178b937d0c4173b0fdcd6bf10a858cfe4f428"
Unverified
Commit
f58eb70e
authored
Oct 23, 2024
by
Daniël de Kok
Committed by
GitHub
Oct 23, 2024
Browse files
Make moe-kernels and marlin-kernels mandatory in CUDA installs (#2632)
parent
9c9ef37c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
server/Makefile
server/Makefile
+1
-1
No files found.
server/Makefile
View file @
f58eb70e
...
@@ -31,7 +31,7 @@ install: install-cuda
...
@@ -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
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment