# mistral-small-4-heretic .env — copy to .env on ana-ml2 (gitignored).
# Easiest: copy the official stack's live .env and change MISTRAL_CONTAINER_NAME,
# so API_KEY (== litellm's VLLM_API_KEY) and HF_TOKEN carry over unchanged —
# that key match is what lets litellm authenticate to this backend with no edit.

# v0.22.0 = the last vLLM before the Mistral multimodal regression (#44911);
# verified working vision tower. Matches the official stack's pin.
MISTRAL_IMAGE=vllm/vllm-openai:v0.22.0

# Distinct from the official's vllm-mistral4 so both can exist on disk; only one
# runs at a time (shared GPU0 + port 8010).
MISTRAL_CONTAINER_NAME=vllm-mistral4-heretic

# Same port + GPU as the official → true drop-in after the official is downed.
MISTRAL_PORT=8010
MISTRAL_GPU_ID=0
MISTRAL_GPU_MEM_UTIL=0.93
MISTRAL_MAX_MODEL_LEN=262144
MISTRAL_MAX_NUM_SEQS=32

# Must equal the official stack's API_KEY (== litellm VLLM_API_KEY env). Carried
# over by copying the official .env. Real value lives on the host, gitignored.
API_KEY=
HF_TOKEN=