set cache reuse to 1

This commit is contained in:
2026-05-07 11:28:09 -05:00
parent ebcc0cf045
commit e56d29528f

View File

@@ -46,7 +46,7 @@ spec:
- name: NIM_MAX_MODEL_LEN - name: NIM_MAX_MODEL_LEN
value: "32768" value: "32768"
- name: NIM_ENABLE_KV_CACHE_REUSE - name: NIM_ENABLE_KV_CACHE_REUSE
value: "true" value: "1"
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"