vh
f08b6cbddf
Replaces the ad-hoc docker-run seats with proper compose stacks on ana-ml2, mirrored here: - meromero-charrp: G4-MeroMero-v2-31B NVFP4A16, char-rp prose (non-thinking, multimodal, vision-enabled), GPU0, 256K @ ~2x. util 0.52 (leaves ~4.6GB GPU0 headroom). - darkscarlett-charrp-reasoning: Dark-Scarlett-v1.0-27B NVFP4A16 (Qwen wrapper recipe), char-rp-reasoning thinking seat, GPU1, 256K. MTP deferred (no spec-decode). Both survive reboot now. Supersede the retired char-rp-gguf + heretic2-charrp-reasoning stacks.
70 lines
2.3 KiB
YAML
70 lines
2.3 KiB
YAML
# meromero-charrp — G4-MeroMero-v2-31B NVFP4A16 char-rp PROSE seat (non-thinking, MULTIMODAL)
|
|
# on ana-ml2 GPU0. Replaces the retired Magidonia GGUF seat (char-rp-gguf / llama-charrp).
|
|
#
|
|
# Gemma-4 dense but with SLIDING-WINDOW attention -> KV-efficient, serves the full native 256K
|
|
# at ~2x concurrency. Vision enabled: preprocessor_config.json was materialized from
|
|
# processor_config.json's image_processor section (Gemma4ImageProcessor); audio is
|
|
# config-declared but weightless (no audio tensors) so it serves image + text.
|
|
#
|
|
# Co-located on GPU0 with vllm-aeon-gen (gen). util 0.52 leaves ~5GB GPU0 headroom
|
|
# (0.55 left only ~1.8GB). Tunables in .env.
|
|
|
|
name: meromero-charrp
|
|
|
|
services:
|
|
vllm-meromero-rp:
|
|
image: ${MEROMERO_IMAGE:-vllm/vllm-openai:latest}
|
|
container_name: ${MEROMERO_CONTAINER:-vllm-meromero-rp}
|
|
restart: unless-stopped
|
|
ipc: host
|
|
ports:
|
|
- "${MEROMERO_PORT:-8016}:8000"
|
|
volumes:
|
|
- /tank/aimodels:/tank/aimodels
|
|
environment:
|
|
- PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
|
- VLLM_API_KEY=${API_KEY:-}
|
|
command:
|
|
- ${MEROMERO_MODEL:-/tank/aimodels/meromero-v2-nvfp4-work/G4-MeroMero-v2-31B-NVFP4A16}
|
|
- --quantization
|
|
- compressed-tensors
|
|
- --served-model-name
|
|
- char-rp
|
|
- --max-model-len
|
|
- "${MEROMERO_MAX_MODEL_LEN:-262144}"
|
|
- --max-num-seqs
|
|
- "${MEROMERO_MAX_NUM_SEQS:-32}"
|
|
- --gpu-memory-utilization
|
|
- "${MEROMERO_GPU_MEM_UTIL:-0.52}"
|
|
- --kv-cache-dtype
|
|
- fp8
|
|
- --trust-remote-code
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${MEROMERO_GPU_ID:-0}"
|
|
capabilities:
|
|
- gpu
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 600s
|
|
networks:
|
|
- tnet
|
|
labels:
|
|
- homepage.group=AI - Inference
|
|
- homepage.name=char-rp (MeroMero-v2 NVFP4, multimodal)
|
|
- homepage.icon=mdi-drama-masks
|
|
- homepage.description=G4-MeroMero-v2-31B NVFP4A16 non-thinking prose seat, vision-enabled, 256K (ana-ml2 GPU0)
|
|
- homepage.href=http://10.250.50.54:${MEROMERO_PORT:-8016}/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|