Multiple update from copilot · c254ef72fa - vllm - SDA Corporation

stephane.david/vllm

Multiple update from copilot

This commit is contained in:

thedarty

2026-09-07 15:55:12 +02:00

parent 5581dff8c1

commit c254ef72fa

1 changed files with 0 additions and 1 deletions

									
										docker-compose.yml
									
		-1
	
												View File
												
					@@ -9,7 +9,6 @@ services:

					      - VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0

					      - VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0

					    ipc: host

					    ipc: host

					    command: >

					    command: >

					      vllm serve

					      --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 0.97

					      --gpu-memory-utilization 0.97