request to both nodes in integration test, dont preload the model - exo should be robust against that

32bb44b3a2825628e0d114324500efd2c798a219 · 2024-08-02 11:51:53 +0100 · Alex Cheema

Files touched

M .circleci/config.yml

Diff

commit 32bb44b3a2825628e0d114324500efd2c798a219
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Fri Aug 2 11:51:53 2024 +0100

    request to both nodes in integration test, dont preload the model - exo should be robust against that
---
 .circleci/config.yml | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/.circleci/config.yml b/.circleci/config.yml
index 88ac43df..083094cc 100644
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@@ -117,18 +117,6 @@ jobs:
             # Check processes before proceeding
             check_processes
 
-            # first one to load the model
-            curl -s http://localhost:8000/v1/chat/completions \
-                -H "Content-Type: application/json" \
-                -d '{
-                  "model": "llama-3.1-8b",
-                  "messages": [{"role": "user", "content": "Keep responses concise. Placeholder to load model..."}],
-                  "temperature": 0.7
-                }'
-
-            # Check processes after model load
-            check_processes
-
             response_1=$(curl -s http://localhost:8000/v1/chat/completions \
               -H "Content-Type: application/json" \
               -d '{
@@ -141,7 +129,7 @@ jobs:
             # Check processes after first response
             check_processes
 
-            response_2=$(curl -s http://localhost:8000/v1/chat/completions \
+            response_2=$(curl -s http://localhost:8001/v1/chat/completions \
               -H "Content-Type: application/json" \
               -d '{
                 "model": "llama-3.1-8b",

← c06124c6 fix circleci badge · back to Exo · run integration test for each inference engine 08e8cacf →