2026-05-29 08:55:10 +00:00
|
|
|
# WAN run on leased vast.ai GPUs. Copy to profiles/local.env and fill in the
|
|
|
|
|
# relay URL + image; keep that copy untracked.
|
|
|
|
|
#
|
2026-05-30 07:51:22 +00:00
|
|
|
# PP_PROFILE=profiles/local.env cargo run --bin pp-orchestrator -- \
|
2026-05-29 08:55:10 +00:00
|
|
|
# --vastai --api-key "$VASTAI_API_KEY"
|
|
|
|
|
#
|
|
|
|
|
# All nodes home onto one operator-controlled relay so they can hole-punch /
|
|
|
|
|
# fall back to relaying across the public internet.
|
|
|
|
|
|
|
|
|
|
# Required for WAN: the relay every container connects through. PLACEHOLDER —
|
2026-06-23 20:10:41 +00:00
|
|
|
# replace with your iroh-driver-relay endpoint in profiles/local.env.
|
2026-05-29 08:55:10 +00:00
|
|
|
SWACTOR_IROH_RELAY_URL=https://relay.example.com
|
|
|
|
|
|
|
|
|
|
NUM_STAGES=2
|
|
|
|
|
PP_IMAGE=swactor-pp-gpu:latest
|
2026-05-30 07:51:22 +00:00
|
|
|
# GPU filters are optional. Leave both unset to let any verified 1-GPU offer
|
|
|
|
|
# qualify (a 1B model fits anywhere). Set PP_GPU="RTX 3060" to pin a model, and/or
|
|
|
|
|
# PP_GPU_MIN_RAM_MB=8000 to require a VRAM floor.
|
|
|
|
|
# llama3.2:1b -> HF Llama-3.2-1B-Instruct-Q6_K.gguf (16 blocks, sharded across
|
|
|
|
|
# the N stages by compute_layer_range; validated key baked into the image).
|
|
|
|
|
MODEL=llama3.2:1b
|
2026-05-29 08:55:10 +00:00
|
|
|
MAX_TOKENS=64
|
