From a845b6b3147e5207657f7fb5a8bc38c97f4979ab Mon Sep 17 00:00:00 2001
From: Gary van Woerkens <gary.van-woerkens@sg.social.gouv.fr>
Date: Fri, 9 Aug 2024 15:11:48 +0200
Subject: [PATCH] fix: disable max-parallel-loading-workers

---
 docker-compose.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docker-compose.yaml b/docker-compose.yaml
index 70abd39..267c824 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -6,7 +6,7 @@ services:
     command:
       - "--model=${MODEL:-mistralai/Mistral-7B-v0.1}"
       - "--tensor-parallel-size=4"
-      - "--max-parallel-loading-workers=1"
+      # - "--max-parallel-loading-workers=1"
       - "--dtype=half" # https://github.com/vllm-project/vllm/issues/1157
     expose:
       - "8000"