32 lines
803 B
YAML
32 lines
803 B
YAML
# enginex-bi100-compat 的启动配置
|
||
#
|
||
# 与平台 bi-100 × vllm × text-generation 的原生 build-config 逐项一致，
|
||
# 只把 command 换成「先过 preflight 再 exec 原命令」：
|
||
# python3 /workspace/compat/serve.py -- <原 command...>
|
||
#
|
||
# 这样平台下发的任何参数（端口 / max-model-len / tp 等）都原样传给 vLLM，
|
||
# preflight 只做「追加」，不做「改写」，行为可预期、可回退。
|
||
concurrency: 1
|
||
command:
|
||
- python3
|
||
- /workspace/compat/serve.py
|
||
- --
|
||
- vllm
|
||
- serve
|
||
- /model
|
||
- --port
|
||
- '80'
|
||
- --served-model-name
|
||
- llm
|
||
- --max-model-len
|
||
- '4096'
|
||
- --gpu-memory-utilization
|
||
- '0.9'
|
||
- --enforce-eager
|
||
- --trust-remote-code
|
||
- -tp
|
||
- '1'
|
||
env:
|
||
- name: PYTHONPATH
|
||
value: /workspace/compat/shims:/workspace/compat
|