From 76fef7b1d260c1f04be552a1d30eb2b5816377d6 Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Tue, 4 Jun 2024 13:31:43 +0000
Subject: [PATCH] Don't install flahs on the CPU tests.

---
 .github/workflows/tests.yaml | 2 +-
 Makefile                     | 6 ++++++
 server/Makefile              | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/tests.yaml b/.github/workflows/tests.yaml
index 37dc8305..74479cc6 100644
--- a/.github/workflows/tests.yaml
+++ b/.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
diff --git a/Makefile b/Makefile
index b22987cb..a949be37 100644
--- a/Makefile
+++ b/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
 
diff --git a/server/Makefile b/server/Makefile
index 089917ce..05e3ac52 100644
--- a/server/Makefile
+++ b/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