From f6e569c0e81f8d7a39808148e7629eebf6678687 Mon Sep 17 00:00:00 2001 From: rock Date: Tue, 27 Oct 2026 23:59:28 -0700 Subject: [PATCH] fix(llm-serving): clef-flash asks for memory the node can reserve worker-1 holds 64Gi and the other predictors request about 55Gi, so the 16Gi request left clef-flash Pending with '0/4 nodes are available: 1 Insufficient memory'. The weights live on the GPU; host memory covers SGLang's own bookkeeping, so 8Gi is the honest reservation. The 32Gi limit stays, so a burst still gets the room. --- k8s/apps/llm-serving/clef-flash.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/k8s/apps/llm-serving/clef-flash.yaml b/k8s/apps/llm-serving/clef-flash.yaml index 4464506..c2749bf 100644 --- a/k8s/apps/llm-serving/clef-flash.yaml +++ b/k8s/apps/llm-serving/clef-flash.yaml @@ -104,7 +104,12 @@ spec: nvidia.com/gpu: '1' requests: cpu: '8' - memory: 16Gi + # 8Gi, not 16Gi. worker-1 holds 64Gi and the other predictors already + # request about 55Gi, so a 16Gi request left the pod Pending forever: + # "1 Insufficient memory". The weights live on the GPU, so host memory is + # for SGLang's own bookkeeping. The limit stays at 32Gi, so a burst that + # needs more is allowed; only the scheduler reservation is smaller. + memory: 8Gi nvidia.com/gpu: '1' startupProbe: # The image is large and the checkpoint is 18.8 GB on first pull.