Update vllm to version 0.9.2 with enhanced model and configuration

This commit is contained in:
2026-08-01 20:31:26 +00:00
parent 763ac922d5
commit 22aeffbd00
2 changed files with 12 additions and 5 deletions

View File

@@ -1,8 +1,8 @@
version: 0.5.4-7
version: 0.9.2-1
defaultConfig:
namespace: llm
model: Qwen/Qwen2.5-7B-Instruct
maxModelLen: 8192
model: Qwen/Qwen3-8B
maxModelLen: 32768
gpuMemoryUtilization: 0.9
cpuRequest: '4'
cpuLimit: '8'