use defaults

2026-05-11 11:36:59 -05:00
parent db6efb188c
commit 2d2df4bb0a
1 changed files with 0 additions and 4 deletions
--- a/clusters/k3s-dgx/nim-service/qwen.yaml
+++ b/clusters/k3s-dgx/nim-service/qwen.yaml
@@ -64,10 +64,6 @@ spec:
    - --max-num-seqs
    - "254"                   # ↑ Allow more concurrent sequences
    - --enable-prefix-caching
-    - --dtype
-    - "float"                # Explicit FP8 encoding
-    - --quantization
-    - "fp8"            # Explicit quantization backend
  authSecret: hf-api-secret
  storage:
    sharedMemorySizeLimit: 64Gi