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.
77 lines
2.5 KiB
YAML
77 lines
2.5 KiB
YAML
# darkscarlett-charrp-reasoning — Dark-Scarlett-v1.0-27B NVFP4A16 char-rp-reasoning seat
|
|
# (THINKING default) on ana-ml2 GPU1. Replaces the retired heretic2-charrp-reasoning seat.
|
|
#
|
|
# Qwen3.6 hybrid GatedDeltaNet linear-attention -> KV-cheap, serves the full native 256K.
|
|
# Quantized with llm-compressor NVFP4A16 loaded through the Qwen3_5ForConditionalGeneration
|
|
# WRAPPER class (an AutoModelForCausalLM save produces a flat config vLLM/SGLang both reject;
|
|
# the wrapper keeps the config they accept). Served --language-model-only (text RP).
|
|
# MTP was dropped by the quant loader -> deferred -> NO --speculative-config.
|
|
#
|
|
# Co-located on GPU1 with the utility model cluster (rerankers/embed/reward/selene/coder/lfm).
|
|
# Tunables in .env.
|
|
|
|
name: darkscarlett-charrp-reasoning
|
|
|
|
services:
|
|
vllm-darkscarlett-rp:
|
|
image: ${DS_IMAGE:-vllm/vllm-openai:latest}
|
|
container_name: ${DS_CONTAINER:-vllm-darkscarlett-rp}
|
|
restart: unless-stopped
|
|
ipc: host
|
|
ports:
|
|
- "${DS_PORT:-8018}:8000"
|
|
volumes:
|
|
- /tank/aimodels:/tank/aimodels
|
|
environment:
|
|
- PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
|
- VLLM_API_KEY=${API_KEY:-}
|
|
command:
|
|
- ${DS_MODEL:-/tank/aimodels/darkscarlett-nvfp4-work/Dark-Scarlett-v1.0-27B-NVFP4A16-wrapper}
|
|
- --quantization
|
|
- compressed-tensors
|
|
- --language-model-only
|
|
- --served-model-name
|
|
- char-rp-reasoning
|
|
- --reasoning-parser
|
|
- qwen3
|
|
- --tool-call-parser
|
|
- qwen3_coder
|
|
- --enable-auto-tool-choice
|
|
- --max-model-len
|
|
- "${DS_MAX_MODEL_LEN:-262144}"
|
|
- --max-num-seqs
|
|
- "${DS_MAX_NUM_SEQS:-32}"
|
|
- --gpu-memory-utilization
|
|
- "${DS_GPU_MEM_UTIL:-0.44}"
|
|
- --kv-cache-dtype
|
|
- fp8
|
|
- --trust-remote-code
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${DS_GPU_ID:-1}"
|
|
capabilities:
|
|
- gpu
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 600s
|
|
networks:
|
|
- tnet
|
|
labels:
|
|
- homepage.group=AI - Inference
|
|
- homepage.name=char-rp-reasoning (Dark-Scarlett NVFP4)
|
|
- homepage.icon=mdi-brain
|
|
- homepage.description=Dark-Scarlett-v1.0-27B NVFP4A16 thinking seat, 256K (ana-ml2 GPU1)
|
|
- homepage.href=http://10.250.50.54:${DS_PORT:-8018}/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|