biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Revert "[V0 deprecation] Remove V0 CPU/XPU/TPU backends (#20412)"
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details

Browse Source 
This reverts commit e202dd2736.
This commit is contained in:
simon-mo
2025-07-06 14:02:36 -07:00
parent c18b3b8e8b
commit a5dd03c1eb
20 changed files with 5034 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/online_serving/chart-helm/values.yaml
View File

@@ -8,7 +8,7 @@ image:
# -- Image tag
tag: "latest"
# -- Container launch command
command: ["vllm", "serve", "/data/", "--served-model-name", "opt-125m", "--enforce-eager", "--dtype", "bfloat16", "--block-size", "16", "--host", "0.0.0.0", "--port", "8000"]
command: ["vllm", "serve", "/data/", "--served-model-name", "opt-125m", "--dtype", "float32", "--block-size", "16", "--host", "0.0.0.0", "--port", "8000"]
# -- Container port
containerPort: 8000