From ea771ff70be037102f4ad49230ecf4f687a7f80e Mon Sep 17 00:00:00 2001 From: biondizzle Date: Tue, 19 May 2026 09:23:10 +0000 Subject: [PATCH] Reduce max_model_len to 512 for initial container test --- docker-compose.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker-compose.yml b/docker-compose.yml index 3c6215e7..d0a18301 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -24,7 +24,7 @@ services: - --reasoning-parser=deepseek_v4 - --moe-backend=cutedsl - --gpu-memory-utilization=0.9 - - --max-model-len=32768 + - --max-model-len=512 - --host=0.0.0.0 - --port=8000 deploy: