Infrastructure/Gluttony-Cluster
2
1
Fork 0
Code Issues 13 Pull Requests Packages Wiki Activity

Update dtype param
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse Source
This commit is contained in:
Tyler Perkins 2024-03-30 22:45:48 -04:00
parent 765124c106
commit ffeadbebff
Signed by: tyler
GPG Key ID: 03B27509E17EFDC8
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/vllm-deployment.yaml
View File

@ -21,7 +21,7 @@ spec:
resources: resources:
limits: limits:
nvidia.com/gpu: 1 nvidia.com/gpu: 2
env: env:
- name: HUGGING_FACE_HUB_TOKEN - name: HUGGING_FACE_HUB_TOKEN
value: "" value: ""
@ -38,6 +38,7 @@ spec:
"--disable-log-requests", "--disable-log-requests",
"--trust-remote-code", "--trust-remote-code",
"--port=8000", "--port=8000",
"--dtype=half",
"--tensor-parallel-size=1"] "--tensor-parallel-size=1"]
ports: ports:
- containerPort: 8000 - containerPort: 8000