# Purpose: every setting the Part 20 scripts read. Copy this file to `.env` beside the
#          scripts and fill in the empty lines for your own machines. Nothing here is a
#          secret except the Hugging Face token, which you generate rather than copy, and
#          which the scripts read from the environment and never write anywhere.
# Platform: all (the Spark values matter on Track S; the two-card values on Track N)
# Minimum memory: 128 GB per node for the two-Spark path; 24 GB per GPU for the two-card path
# Assumes: `cp env-example.txt .env`, then an editor. Every script loads it with
#          `set -a; . ./.env; set +a` when the file is present, so a value set in your
#          shell always wins over a value in the file.

# ------------------------------------------------------------------- the two machines
# Addresses on the direct QSFP link, NOT on the house network. Take them from
# `ip addr show <interface>` after the connect-two-Sparks playbook has assigned them.
# The playbook's example puts the first port's pair on a 192.168.100.0/24 subnet and the
# second port's pair on 192.168.101.0/24, one host address per node in each.
# This node's own address on the link. Different on each machine.
NODE_SELF_ADDR=

# The head node's address on the link. The SAME value on both machines: on the head it
# equals NODE_SELF_ADDR, on the worker it is the head's address.
NODE_HEAD_ADDR=

# The other machine's address on the link, used by prepare-spark-pair.sh for its
# reachability and SSH checks. Different on each machine.
NODE_PEER_ADDR=

# The login name that exists on BOTH machines. The playbooks require it to match.
CLUSTER_USER=

# ------------------------------------------------------------------ the link itself
# The QSFP interface that came up, from `ibdev2netdev`. The playbook's validated example
# on a DGX Spark is enp1s0f1np1; confirm yours rather than copying this one.
CX7_IFNAME=enp1s0f1np1

# The RoCE device paired with that interface in the same ibdev2netdev output, without the
# trailing port number. Used as the NCCL_IB_HCA filter. Leave empty to let NCCL choose.
CX7_ROCE_DEV=

# The management interface you SSH in on, used only for the NCCL test suite's bootstrap,
# which NVIDIA's NCCL playbook launches over the management network.
MGMT_IFNAME=

# ------------------------------------------------------------------------ containers
# The NGC vLLM image for your hardware. Take the current tag from the DGX Spark vLLM
# playbook's Instructions tab; it changes, and both nodes must use the same one.
VLLM_IMAGE=

# The TensorRT-LLM release image, if you take the playbook path in the optional task.
# Three NVIDIA pages named three different tags on 2026-09-09: check NGC.
TRTLLM_IMAGE=

# ---------------------------------------------------------------------------- models
# Where models live on each node. The same path on both machines, as vLLM's multi-node
# documentation requires, or a filesystem both can read.
HF_HOME=

# The very large model served across the pair. The vLLM multi-node playbook's optional
# 405B step uses hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4, published under the
# Llama 3.1 Community licence: read the model card before using it.
PAIR_MODEL=hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4

# The single-machine comparison. gpt-oss-120b is Apache-2.0 with native MXFP4 weights.
SINGLE_MODEL=openai/gpt-oss-120b

# The two-card desktop fallback. hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4 is
# the 70B-class option and is tight on 2x24 GB; Qwen/Qwen3-32B-AWQ is the comfortable one.
TWO_CARD_MODEL=hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4

# The name clients send in the "model" field. Keep it stable across every path so the
# load generator's command line does not change between runs.
SERVED_NAME=local-cluster

# ------------------------------------------------------------------------- serving
SERVE_HOST=127.0.0.1
SERVE_PORT=8000

# Context length. The vLLM playbook's 405B step uses 64 because there is no headroom;
# raise it for the single-machine and two-card paths and record what you used.
CTX=4096

# Fraction of each device the engine may claim, and sequences in flight.
MEM_FRACTION=0.90
MAX_SEQS=4

# --------------------------------------------------------------------------- secrets
# Gated models need a Hugging Face token. Export it in your shell rather than writing it
# here if you can; if you do put it here, keep .env out of version control.
HF_TOKEN=

# The load generator reads an API key, if the server needs one, from the variable named
# here. It is never written to the notebook.
LOADTEST_API_KEY_ENV=LOADTEST_API_KEY