stephane.david/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add some parameters to command

Browse Source
This commit is contained in:
thedarty
2026-09-07 16:17:02 +02:00
parent b8fc00685f
commit cb175afb22
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker-compose.yml
+2 -1
View File
@@ -5,13 +5,14 @@ services:
network_mode: bridge network_mode: bridge
environment: environment:
- HF_TOKEN=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 - HF_TOKEN=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
- VLLM_GPU_MEMORY_UTILIZATION=0.97
- VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0 - VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
ipc: host ipc: host
command: > command: >
--model Qwen/Qwen2.5-14B-Instruct-AWQ --model Qwen/Qwen2.5-14B-Instruct-AWQ
--max-model-len 8192 --max-model-len 8192
--gpu-memory-utilization 0.95 --gpu-memory-utilization 0.95
--enable-auto-tool-choice
--tool-call-parser default
ports: ports:
- "8000:8000" - "8000:8000"
volumes: volumes: