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

Update node to watch forever
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse Source
This commit is contained in:
Tyler Perkins 2024-03-30 22:20:50 -04:00
parent e78ac932d0
commit 17e076e0c8
Signed by: tyler
GPG Key ID: 03B27509E17EFDC8
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
vllm/vllm-deployment.yaml
View File

@ -28,13 +28,14 @@ spec:
value: /.cache value: /.cache
- name: shm-size - name: shm-size
value: 1g value: 1g
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["watch", "ls"]
args: ["--model=meta-llama/Llama-2-7b-hf", #command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
"--gpu-memory-utilization=0.95", #args: ["--model=meta-llama/Llama-2-7b-hf",
"--disable-log-requests", # "--gpu-memory-utilization=0.95",
"--trust-remote-code", # "--disable-log-requests",
"--port=8000", # "--trust-remote-code",
"--tensor-parallel-size=1"] # "--port=8000",
# "--tensor-parallel-size=1"]
ports: ports:
- containerPort: 8000 - containerPort: 8000
name: http name: http