sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix vllm and tini

Browse source
This commit is contained in:
sirius0xdev 2026-05-10 01:48:34 +00:00
parent 3d3f0a5a1f
commit bce6e18f2b
2 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
apps/base/customer1/hermes-agent/new-deployment.yaml
View file

@ -103,7 +103,8 @@ spec:
secretKeyRef: secretKeyRef:
name: telegram-webhook name: telegram-webhook
key: TELEGRAM_WEBHOOK_SECRET key: TELEGRAM_WEBHOOK_SECRET
- name: TINI_SUBREAPER
value: "true"
- name: TELEGRAM_WEBHOOK_PORT - name: TELEGRAM_WEBHOOK_PORT
value: "8645" value: "8645"

2
infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
View file

@ -42,7 +42,7 @@ spec:
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --kv-cache-dtype=fp8 - --kv-cache-dtype=fp8
- --max-num-batched-tokens=65536 - --max-num-batched-tokens=65536
- --max-num-seqs=128 - --max-num-seqs=64
- --enable-chunked-prefill - --enable-chunked-prefill
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto