marco/veda
1
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

LiteLLM: added max_parallel_requests

Browse Source
This commit is contained in:
Marco van Zijl 2026-06-02 20:32:56 +02:00
parent 0a2cbc4c25
commit 96f364def0
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
apps/litellm/values.yaml
View File

@ -59,11 +59,13 @@ litellm:
model_info: model_info:
mode: chat mode: chat
max_input_tokens: 131072 max_input_tokens: 131072
max_parallel_requests: 1
- model_name: qwen122 - model_name: qwen122
litellm_params: litellm_params:
model: openai/qwen122 model: openai/qwen122
api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1 api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1
api_key: not-needed api_key: not-needed
max_parallel_requests: 1
model_info: model_info:
mode: chat mode: chat
max_input_tokens: 262144 max_input_tokens: 262144
@ -73,6 +75,7 @@ litellm:
model: openai/qwen122-abliterated model: openai/qwen122-abliterated
api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1 api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1
api_key: not-needed api_key: not-needed
max_parallel_requests: 1
model_info: model_info:
mode: chat mode: chat
max_input_tokens: 262144 max_input_tokens: 262144