vh
6851ecbd0b
meromero-rp sized its KV from --gpu-memory-utilization, and vLLM's profile counts co-booting neighbours as its own non-torch memory. Three boots gave 20.37 / 26.74 / 29.04 GiB of KV, and the 2026-10-05 Docker-move restart cut GPU 1 free memory to 3,981 MiB, below intern-decision's 32k-token budget. Coder read negative KV on every co-boot. Both are now pinned, so util only gates the boot check (meromero util 0.52 -> 0.47, just above its footprint). GPU 0 plateaus at ~60 MiB free 1-2 days after a boot (Beszel), so gen-small's KV drops to 5.5 GiB (461,215 tokens, 1.76x) and parakeet-nemo stays on GPU 0 with room for its 3,840 MiB cap. GPU 3 stays clear. Applied with playbooks/fv-ml1-kv-pin-20261005.yaml: GPU 1 free 3,981 -> 11,801 MiB, GPU 0 495 -> 5,039 MiB right after boot; all nine seats healthy.
110 lines
4.8 KiB
YAML
110 lines
4.8 KiB
YAML
# meromero-charrp — G4-MeroMero-v2-31B NVFP4A16 char-rp PROSE seat (non-thinking, MULTIMODAL)
|
|
# on fv-ml1 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:
|
|
- ${MEROMERO_MODEL:-/tank/aimodels/meromero-v2-nvfp4-work/G4-MeroMero-v2-31B-NVFP4A16}
|
|
- --quantization
|
|
- compressed-tensors
|
|
- --served-model-name
|
|
- char-rp
|
|
- char-rp-thinking
|
|
# Tool-calling: Gemma-4 emits its OWN native syntax
|
|
# (<|tool_call>call:name{...}<tool_call|>), NOT the qwen3_coder XML the
|
|
# other seats use. vLLM 0.24 ships a matching `gemma4` parser whose token
|
|
# constants line up with this tokenizer's etc/eoc/escape tokens exactly.
|
|
# Without these two flags any tools-bearing request 400s outright.
|
|
- --tool-call-parser
|
|
- gemma4
|
|
- --enable-auto-tool-choice
|
|
# The gemma4 REASONING parser is what absorbs the <|channel>...<channel|>
|
|
# thought markers; without it they leak into `content` verbatim on the
|
|
# post-tool-response turn (upstream vllm #45834 — the chat template leaves
|
|
# the prompt inside an open channel block).
|
|
- --reasoning-parser
|
|
- gemma4
|
|
# Dwarf-panel CoT patch 2026-08-21: force-open <|channel> on enable_thinking:true
|
|
- --chat-template
|
|
- /tank/aimodels/meromero-v2-nvfp4-work/patched_chat_template.jinja
|
|
# MANDATORY companion to the reasoning parser on this seat. The parser
|
|
# reads enable_thinking from chat_template_kwargs and DEFAULTS IT TO TRUE
|
|
# (vllm/parser/gemma4.py:439). True makes is_reasoning_end() return False
|
|
# at a new turn, which pre-initialises the engine to REASONING -> ALL plain
|
|
# RP prose lands in reasoning_content with a NULL content, breaking every
|
|
# char-rp consumer. This template already defaults enable_thinking to false
|
|
# (chat_template.jinja:350), so passing it explicitly renders a BYTE-
|
|
# IDENTICAL prompt (verified across plain/tools/post-tool/system shapes) --
|
|
# it only corrects the parser's state machine. Do not remove.
|
|
- --default-chat-template-kwargs
|
|
- '{"enable_thinking": false}'
|
|
- --max-model-len
|
|
- "${MEROMERO_MAX_MODEL_LEN:-262144}"
|
|
- --max-num-seqs
|
|
- "${MEROMERO_MAX_NUM_SEQS:-32}"
|
|
- --gpu-memory-utilization
|
|
- "${MEROMERO_GPU_MEM_UTIL:-0.47}"
|
|
# KV pinned in bytes (2026-10-05, Prime: 22 GiB). Util-sized KV was a lottery on
|
|
# this shared card: vLLM's profile counts co-booting neighbours as its own non-torch
|
|
# memory, so three boots gave 20.37 / 26.74 / 29.04 GiB of KV. With this set, vLLM
|
|
# skips profiling and util only gates the boot check (Free at start >= util x total),
|
|
# so util stays just above the real footprint (~43.6 GiB).
|
|
- --kv-cache-memory
|
|
- "${MEROMERO_KV_CACHE_MEMORY:-23622320128}"
|
|
- --kv-cache-dtype
|
|
- fp8
|
|
- --trust-remote-code
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${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:
|
|
# STOPPED 2026-08-24 — superseded by stacks/gemma4-charrp (gemma-4-26B-A4B
|
|
# -it NVFP4 MoE) on the same port and the same served-model-names. Kept as
|
|
# the rollback seat: `docker compose up -d vllm-meromero-rp` here after
|
|
# stopping the gemma4 one, since both want :8016.
|
|
- homepage.group=AI - Dormant
|
|
- homepage.name=char-rp (MeroMero-v2 NVFP4) — rollback
|
|
- homepage.icon=mdi-drama-masks
|
|
- homepage.description=Superseded 2026-08-24 by the Gemma-4 26B-A4B MoE seat; dense 31B NVFP4A16, kept for rollback (fv-ml1 GPU0)
|
|
- homepage.href=http://10.251.50.54:${MEROMERO_PORT:-8016}/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|