vh
911ff20356
- services/erp-seat-quant/quant_nvfp4a16_gemma4_moe.py: linearize_moe first (playbook §3.15), asserts the expert Linear count, routers/vision/audio/norms/lm_head ignored, W4A16 for RP long-session fidelity, post-steps restore processor configs + template and reset the tokenizer truncation cap (§3.14); --dry-run proves targets before GPU time - services/erp-seat-quant/run_quant_erp_v6.sh: detached container on GPU1 (vllm-llmcompressor) - stacks/erp-seat: serve recipe copied from gemma4-charrp, true served name only, port 8021
77 lines
2.6 KiB
YAML
77 lines
2.6 KiB
YAML
# erp-seat — the ERP-tune seat on ana-ml2 GPU1: NVFP4A16 quant of the latest gated ERP LoRA merge
|
|
# (run 6 = jenerallee78 ARA-abliterated Gemma-4-26B-A4B + R47 SFT), served under its TRUE name.
|
|
# Routing aliases (e.g. LiteLLM `trial`) are the operator's call and live in the gateway, not here.
|
|
#
|
|
# Serve recipe copied from stacks/gemma4-charrp (same architecture + quant format, proven on this
|
|
# box): gemma4 tool + reasoning parsers, enable_thinking pinned false, model's own stock template.
|
|
# GPU1 is SHARED (charrp-MoE moved? no — scriberr, embed, rerank, coder, reward live there):
|
|
# ~47 GiB was free on 2026-09-08; 0.35 x 97.9 GiB = 34 GiB keeps ~13 GiB of real margin.
|
|
# Quant pipeline: services/erp-seat-quant/. Tunables in .env.
|
|
|
|
name: erp-seat
|
|
|
|
services:
|
|
vllm-erp-seat:
|
|
image: ${ERP_IMAGE:-vllm/vllm-openai:v0.26.0}
|
|
container_name: ${ERP_CONTAINER:-vllm-erp-seat}
|
|
restart: unless-stopped
|
|
ipc: host
|
|
ports:
|
|
- "${ERP_PORT:-8021}:8000"
|
|
volumes:
|
|
- /tank/aimodels:/tank/aimodels
|
|
environment:
|
|
- VLLM_API_KEY=${API_KEY:-}
|
|
command:
|
|
- ${ERP_MODEL:-/tank/aimodels/erp-tune-v6-nvfp4a16}
|
|
- --quantization
|
|
- compressed-tensors
|
|
- --served-model-name
|
|
- ${ERP_SERVED_NAME:-erp-tune-v6-nvfp4a16}
|
|
- --tool-call-parser
|
|
- gemma4
|
|
- --enable-auto-tool-choice
|
|
- --reasoning-parser
|
|
- gemma4
|
|
- --default-chat-template-kwargs
|
|
- '{"enable_thinking": false}'
|
|
- --chat-template
|
|
- ${ERP_CHAT_TEMPLATE:-/tank/aimodels/erp-tune-v6-nvfp4a16/chat_template.jinja}
|
|
- --max-model-len
|
|
- "${ERP_MAX_MODEL_LEN:-32768}"
|
|
- --max-num-seqs
|
|
- "${ERP_MAX_NUM_SEQS:-8}"
|
|
- --gpu-memory-utilization
|
|
- "${ERP_GPU_MEM_UTIL:-0.35}"
|
|
- --kv-cache-dtype
|
|
- fp8
|
|
- --trust-remote-code
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${ERP_GPU_ID:-1}"
|
|
capabilities:
|
|
- gpu
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 600s
|
|
networks:
|
|
- tnet
|
|
labels:
|
|
- homepage.group=AI - Inference
|
|
- homepage.name=erp-tune-v6 (Gemma-4 26B-A4B ARA, NVFP4A16)
|
|
- homepage.icon=mdi-fire
|
|
- homepage.description=ERP-seat run-6 LoRA merge on the jenerallee78 abliteration, NVFP4A16 MoE (ana-ml2 GPU1)
|
|
- homepage.href=http://10.250.50.54:${ERP_PORT:-8021}/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|