fix list

2026-05-11 11:33:45 -05:00
parent 855cce3c54
commit 719a6e3d11
1 changed files with 2 additions and 2 deletions
--- a/clusters/k3s-dgx/nim-service/qwen.yaml
+++ b/clusters/k3s-dgx/nim-service/qwen.yaml
@@ -66,9 +66,9 @@ spec:
    - --enable-prefix-caching
    - --dtype
    - "float8"                # Explicit FP8 encoding
-    --quantization
+    - --quantization
    - "fbgemm-fp8"            # Explicit quantization backend
-    --sv2-transformer-bindings  # Skip SA checks (small speedup)
+    - --sv2-transformer-bindings  # Skip SA checks (small speedup)
  authSecret: hf-api-secret
  storage:
    sharedMemorySizeLimit: 64Gi