Don't install flahs on the CPU tests.

.github/workflows/tests.yaml

@@ -68,7 +68,7 @@ jobs:
             ~/.cargo/git
       - name: Install
         run: |
-          make install
+          make install-cpu
       - name: Run server tests
         run: |
           pip install pytest

Makefile

@@ -1,6 +1,9 @@
 install-server:
 	cd server && make install
 
+install-server-cpu:
+	cd server && make install-server
+
 install-router:
 	cd router && cargo install --path .
 
@@ -12,6 +15,9 @@ install-benchmark:
 
 install: install-server install-router install-launcher
 
+
+install-cpu: install-server-cpu install-router install-launcher
+
 server-dev:
 	cd server && make run-dev
 

server/Makefile

@@ -23,7 +23,7 @@ install-server: gen-server
 	pip install -e ".[bnb, accelerate, quantize, peft, outlines]"
 
 
-install: install-server install-cuda
+install: install-cuda
 	echo "Installed server"
 
 install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention