vh
f566f61b24
Serves the in-house abliterated Mistral Small 4 (heretic NVFP4, vision-intact) under --served-model-name mistral-small-4 on ana-ml2 GPU0:8010 — a true drop-in for the official mistral-small-4 backend. Both litellm entries (mistral-small-4 + mistral-small-4-reasoning) route here with no litellm change. GPU0 fits one mistral-class model, so this is a backend swap, not a co-tenant: bring up after downing the official stack; revert by downing this and up-ing the official. Verified live through the gateway: standard returns clean answers, reasoning populates reasoning_content (the [THINK] split). Checkpoint built per tools/mistral-small4-nvfp4/.
102 lines
3.4 KiB
YAML
102 lines
3.4 KiB
YAML
# mistral-small-4-heretic — abliterated Mistral Small 4 (heretic NVFP4) as a
|
|
# DROP-IN for the official mistral-small-4 backend.
|
|
#
|
|
# Serves darkc0de/Mistral-Small-4-119B-2603-heretic, quantized to NVFP4 in-house
|
|
# (vision tower kept bf16) and converted to Mistral native format. Built + validated
|
|
# 2026-06-17 — see tools/mistral-small4-nvfp4/ for the build pipeline.
|
|
#
|
|
# WHY a separate stack: GPU0 fits only one mistral-class model (~65-70 GB), so this
|
|
# is a backend SWAP, not a co-tenant. Bring it up only after downing the official
|
|
# mistral-small-4 stack. It serves under --served-model-name mistral-small-4 on the
|
|
# SAME port (8010), so litellm's mistral-small-4 + mistral-small-4-reasoning entries
|
|
# route here with NO litellm change. Revert = down this, `up -d` the official stack.
|
|
#
|
|
# DIFFERENCES vs the official compose (everything else mirrors it for a faithful
|
|
# drop-in — TP=1, util 0.93, MLA, reasoning + tool-call parsers, prefix caching):
|
|
# - model is a LOCAL native dir (mounted /model), not an HF id, so it needs the
|
|
# native loader flags: --config-format/--load-format/--tokenizer-mode mistral.
|
|
# - distinct container_name (vllm-mistral4-heretic) so it can be staged without
|
|
# colliding with the official container.
|
|
|
|
name: mistral-small-4-heretic
|
|
|
|
services:
|
|
vllm-mistral4-heretic:
|
|
image: ${MISTRAL_IMAGE}
|
|
container_name: ${MISTRAL_CONTAINER_NAME}
|
|
restart: unless-stopped
|
|
ipc: host
|
|
ports:
|
|
- "${MISTRAL_PORT}:8000"
|
|
volumes:
|
|
- /tank/aimodels/huggingface:/hfcache
|
|
# The in-house heretic native NVFP4 checkpoint (read-only).
|
|
- /tank/aimodels/quant-work/heretic-native-nvfp4:/model:ro
|
|
environment:
|
|
- HF_HOME=/hfcache
|
|
- HF_HUB_CACHE=/hfcache/hub
|
|
- HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
|
|
- VLLM_API_KEY=${API_KEY:-}
|
|
command:
|
|
- /model
|
|
# Native Mistral format (params.json + consolidated*.safetensors + tekken).
|
|
- --config-format
|
|
- mistral
|
|
- --load-format
|
|
- mistral
|
|
- --tokenizer-mode
|
|
- mistral
|
|
# SAME served name as the official → litellm routes here unchanged.
|
|
- --served-model-name
|
|
- mistral-small-4
|
|
- --host
|
|
- 0.0.0.0
|
|
- --port
|
|
- "8000"
|
|
- --tensor-parallel-size
|
|
- "1"
|
|
- --gpu-memory-utilization
|
|
- ${MISTRAL_GPU_MEM_UTIL}
|
|
- --max-model-len
|
|
- ${MISTRAL_MAX_MODEL_LEN}
|
|
- --attention-backend
|
|
- TRITON_MLA
|
|
- --tool-call-parser
|
|
- mistral
|
|
- --enable-auto-tool-choice
|
|
- --reasoning-parser
|
|
- mistral
|
|
- --max-num-seqs
|
|
- ${MISTRAL_MAX_NUM_SEQS}
|
|
- --dtype
|
|
- auto
|
|
- --enable-prefix-caching
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${MISTRAL_GPU_ID}"
|
|
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 Systems
|
|
- homepage.name=Mistral Small 4 (heretic NVFP4)
|
|
- homepage.icon=mdi-creation
|
|
- homepage.description=Abliterated Mistral-Small-4 (heretic NVFP4) drop-in via vLLM (ana-ml2 GPU 0)
|
|
- homepage.href=http://10.250.50.54:${MISTRAL_PORT}/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|