# Mistral Small 4 (official NVFP4) on ana-ml2 GPU 0 — copy to .env on the host.
# Real .env lives on ana-ml2 at /opt/docker/compose/mistral-small-4/.env (gitignored).
#
# See compose.yaml header for the NVFP4/TP=1/MLA rationale and the vLLM>=0.20 floor.

# PINNED by digest, not :latest — this model is version-sensitive (needs vLLM
# >= 0.20 for day-0 support; the related nvidia-ModelOpt NVFP4 MoE path broke on
# 0.19.1/0.22.0). Pin protects against a :latest regression. This digest = vLLM
# 0.23.0, the version validated to load this checkpoint. Bump deliberately.
MISTRAL_IMAGE=vllm/vllm-openai@sha256:6d8429e38e3747723ca07ee1b17972e09bb9c51c4032b266f24fb1cc3b22ed8f

MISTRAL_CONTAINER_NAME=vllm-mistral4
MISTRAL_MODEL=mistralai/Mistral-Small-4-119B-2603-NVFP4
MISTRAL_PORT=8010

# GPU 0 = the free 96 GB Blackwell card, dedicated single-tenant to this model
# (74.4 GB weights leave no room to co-tenant). GPU 1 holds qwen36 + granite +
# the embed/rerank/reward trio.
MISTRAL_GPU_ID=0

# util 0.93 (~89 GB budget) — 74.4 GB weights + ~5 GB CUDA/graph leaves ~10 GB
# KV. MLA keeps KV compressed so 131072 ctx fits; raise toward native 256K only
# after measuring real KV headroom. Dedicated card, so 0.93 is safe.
MISTRAL_GPU_MEM_UTIL=0.93
MISTRAL_MAX_MODEL_LEN=131072
# Single-card KV is tighter than the official TP=2 setup → cap concurrency at 64
# (official used 128 across two cards).
MISTRAL_MAX_NUM_SEQS=64

# Optional — model is ungated (Apache-2.0), no token needed.
HF_TOKEN=
API_KEY=