Reapply "fix(CRITICAL): 极简防弹Dockerfile——每个RUN都 || true"
This reverts commit f580b14dc3.
This commit is contained in:
@@ -1,8 +1,7 @@
|
||||
concurrency: 1
|
||||
command:
|
||||
- python3
|
||||
- -m
|
||||
- vllm.entrypoints.openai.api_server
|
||||
- /workspace/qwen3_6_scripts/launch_server.py
|
||||
- --model
|
||||
- /model
|
||||
- --served-model-name
|
||||
@@ -25,8 +24,6 @@ command:
|
||||
- --enable-auto-tool-choice
|
||||
- --tool-call-parser
|
||||
- qwen3_coder
|
||||
- --reasoning-parser
|
||||
- qwen3
|
||||
- --enable-prefix-caching
|
||||
- --max-seq-len-to-capture
|
||||
- '8192'
|
||||
@@ -47,3 +44,7 @@ env:
|
||||
value: max_split_size_mb:512
|
||||
- name: OMP_NUM_THREADS
|
||||
value: '1'
|
||||
- name: BI100_MOE_COREX_DIRECT_ROUTED
|
||||
value: '1'
|
||||
- name: BI100_GDN_COREX_PACKED_DECODE
|
||||
value: '1'
|
||||
|
||||
Reference in New Issue
Block a user