software-engineering/edge-gitops
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add max model len

Browse Source
This commit is contained in:
HaimKortovich
2026-05-07 11:19:11 -05:00
parent 923679cb29
commit 0997aa48b7
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -35,8 +35,6 @@ spec:
value: "16384" value: "16384"
- name: ENABLE_AUTO_TOOL_CHOICE - name: ENABLE_AUTO_TOOL_CHOICE
value: "true" value: "true"
- name: TOOL_CALL_PARSER
value: "hermes"
- name: ENABLE_PREFIX_CACHING - name: ENABLE_PREFIX_CACHING
value: "true" value: "true"
- name: TRUNCATION_SIDE - name: TRUNCATION_SIDE
@@ -45,6 +43,8 @@ spec:
value: "INFO" value: "INFO"
- name: VLLM_ALLOW_LONG_MAX_MODEL_LEN - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN
value: "true" value: "true"
- name: NIM_MAX_MODEL_LEN
value: "32768"
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"