44 lines
1.1 KiB
YAML
44 lines
1.1 KiB
YAML
services:
|
|
sglang:
|
|
image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
|
|
container_name: ds41-sglang-b4
|
|
shm_size: "32gb"
|
|
ipc: host
|
|
privileged: true
|
|
ports:
|
|
- "30001:30000"
|
|
environment:
|
|
- CUDA_VISIBLE_DEVICES=4,5,6,7
|
|
- PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
|
volumes:
|
|
- /data:/data
|
|
- /data/ymk/cache/sglang:/root/.cache/sglang
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
command: >-
|
|
sglang serve
|
|
--trust-remote-code
|
|
--model-path /data/models/DeepSeek-V4.1-Flash
|
|
--tp 4
|
|
--ep-size 4
|
|
--mem-fraction-static 0.60
|
|
--attention-backend dsv4
|
|
--moe-runner-backend flashinfer_mxfp4
|
|
--cuda-graph-max-bs-decode 64
|
|
--reasoning-parser auto
|
|
--tool-call-parser auto
|
|
--max-running-requests 64
|
|
--host 0.0.0.0
|
|
--port 30000
|
|
--dp-size 4
|
|
--enable-dp-attention
|
|
|
|
--enable-cache-report
|
|
--enable-metrics
|
|
--json-model-override-args '{"vision_n_layers": 0}'
|