Multiple update from copilot
This commit is contained in:
+7
-3
@@ -5,10 +5,14 @@ services:
|
|||||||
network_mode: bridge
|
network_mode: bridge
|
||||||
environment:
|
environment:
|
||||||
- HF_TOKEN=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
|
- HF_TOKEN=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
|
||||||
# - PYTORCH_ALLOC_CONF=expandable_segments:True
|
- VLLM_GPU_MEMORY_UTILIZATION=0.97
|
||||||
# - VLLM_DEVICE=cpu
|
- VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
|
||||||
ipc: host
|
ipc: host
|
||||||
command: --model Qwen/Qwen2.5-14B-Instruct-AWQ
|
command: >
|
||||||
|
vllm serve
|
||||||
|
Qwen/Qwen2.5-14B-Instruct-AWQ
|
||||||
|
--max-model-len 8192
|
||||||
|
--gpu-memory-utilization 0.97
|
||||||
ports:
|
ports:
|
||||||
- "8000:8000"
|
- "8000:8000"
|
||||||
volumes:
|
volumes:
|
||||||
|
|||||||
Reference in New Issue
Block a user