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