From aad0019250ce81d55b159f1a1155a9bba82055ea Mon Sep 17 00:00:00 2001 From: zxw <1020938856@qq.com> Date: Thu, 23 Oct 2025 11:15:41 +0800 Subject: [PATCH] update qwq-32b --- models/alibaba/qwq-32b/metadata.yaml | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/models/alibaba/qwq-32b/metadata.yaml b/models/alibaba/qwq-32b/metadata.yaml index c2ab895..cdf2952 100644 --- a/models/alibaba/qwq-32b/metadata.yaml +++ b/models/alibaba/qwq-32b/metadata.yaml @@ -9,9 +9,11 @@ spec: - customRuntimeArgs: - --max-model-len=32768 - --enforce-eager - - --enable_reasoning - - --reasoning_parser=deepseek_r1 + - --reasoning-parser=deepseek_r1 - --gpu-memory-utilization=1 + - --enable-auto-tool-choice + - --tool-call-parser + - hermes resourceRequirements: cpu: 8 gpuCount: 1