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

fix vllm error

Browse source
This commit is contained in:
sirius0xdev 2026-05-06 01:31:45 +00:00
parent 5247e6caee
commit 2200006c41
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
apps/base/customer1/hermes-agent/rays-deployment.yaml
View file

@ -42,7 +42,7 @@ spec:
key: XAI_API_KEY key: XAI_API_KEY
- name: TELEGRAM_ALLOWED_USERS - name: TELEGRAM_ALLOWED_USERS
value: "" value: "7105451284"
# === Local vLLM (OpenAI-compatible) === # === Local vLLM (OpenAI-compatible) ===
- name: OPENAI_BASE_URL - name: OPENAI_BASE_URL

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

@ -40,7 +40,7 @@ spec:
- --gpu-memory-utilization=0.98 - --gpu-memory-utilization=0.98
- --max-model-len=131072 - --max-model-len=131072
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --kv-cache=dtype=fp8 - --kv-cache-dtype=fp8
- --max-num-batched-tokens=32768 - --max-num-batched-tokens=32768
- --max-num-seqs=16 - --max-num-seqs=16
- --trust-remote-code - --trust-remote-code