enable cache reuse

This commit is contained in:
2026-05-07 11:26:30 -05:00
parent 0997aa48b7
commit ebcc0cf045

View File

@@ -45,6 +45,8 @@ spec:
value: "true" value: "true"
- name: NIM_MAX_MODEL_LEN - name: NIM_MAX_MODEL_LEN
value: "32768" value: "32768"
- name: NIM_ENABLE_KV_CACHE_REUSE
value: "true"
image: image:
repository: nvcr.io/nim/qwen/qwen3-32b-dgx-spark repository: nvcr.io/nim/qwen/qwen3-32b-dgx-spark
tag: "1.1.0-variant" tag: "1.1.0-variant"