From 038f30bd6c3cb6efc8c1a872d53c4944d76e3a2b Mon Sep 17 00:00:00 2001 From: Marc Blatter Date: Fri, 10 Jul 2026 18:35:06 +0000 Subject: [PATCH] compose-vLLM.yaml aktualisiert --- compose-vLLM.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/compose-vLLM.yaml b/compose-vLLM.yaml index 8eb51ed..6507662 100644 --- a/compose-vLLM.yaml +++ b/compose-vLLM.yaml @@ -29,7 +29,7 @@ services: --model Qwen/Qwen2.5-7B-Instruct-AWQ --host 0.0.0.0 --port 8000 - --gpu-memory-utilization 0.75 - --max-model-len 16384 + --gpu-memory-utilization 0.85 + --max-model-len 65536 --enable-auto-tool-choice --tool-call-parser hermes \ No newline at end of file