diff --git a/clusters/k3s-dgx/nim-service/qwen.yaml b/clusters/k3s-dgx/nim-service/qwen.yaml index db19c0b..c42626f 100644 --- a/clusters/k3s-dgx/nim-service/qwen.yaml +++ b/clusters/k3s-dgx/nim-service/qwen.yaml @@ -64,8 +64,6 @@ spec: - --max-num-seqs - "254" # ↑ Allow more concurrent sequences - --enable-prefix-caching - - --swap-space - - "8" authSecret: hf-api-secret storage: sharedMemorySizeLimit: 64Gi