56 lines
1.5 KiB
YAML
56 lines
1.5 KiB
YAML
services:
|
|
sglang:
|
|
image: ymkymx/sglang:dsv41-pd-c74a4037f-20260921-1300
|
|
container_name: ds41-pd-prefill-dp
|
|
shm_size: "32gb"
|
|
ipc: host
|
|
pid: host
|
|
privileged: true
|
|
network_mode: host
|
|
|
|
environment:
|
|
- CUDA_VISIBLE_DEVICES=0,1,2,3
|
|
- SGLANG_RAGGED_VERIFY_MODE=static
|
|
- MC_INTRANODE_NVLINK=true
|
|
- MC_INTRA_NVLINK=true
|
|
- SGLANG_MOONCAKE_SEND_AUX_TCP=1
|
|
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
|
|
--dp-size 4
|
|
--enable-dp-attention
|
|
--enable-dp-lm-head
|
|
--load-balance-method total_tokens
|
|
--mem-fraction-static 0.75
|
|
--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 30010
|
|
--enable-cache-report
|
|
--speculative-algorithm DSPARK
|
|
--speculative-dspark-block-size 5
|
|
--enable-hierarchical-cache
|
|
--hicache-ratio 2.5
|
|
--hicache-write-policy write_back
|
|
--disaggregation-mode prefill
|
|
--disaggregation-bootstrap-port 8918
|
|
--disaggregation-transfer-backend mooncake
|
|
--json-model-override-args '{"vision_n_layers": 0}'
|