fix: remove XFORMERS attention backend override to fix Venice gibberish
This commit is contained in:
parent
eac5d21894
commit
1cc2d8e112
1 changed files with 0 additions and 2 deletions
|
|
@ -27,8 +27,6 @@ spec:
|
|||
image: vllm/vllm-openai:latest
|
||||
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
|
||||
env:
|
||||
- name: VLLM_ATTENTION_BACKEND
|
||||
value: "XFORMERS"
|
||||
- name: HF_TOKEN
|
||||
value: ""
|
||||
- name: VLLM_TOKENIZER_MODE
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue