# Worker tunables — Qwen3.8-27B pipeline-parallel RPC worker (Dankserver).
#
# The worker is the REMOTE side of the split. It exposes the RTX 3090 to the
# head on Dankclaw as an RPC device. It runs from the b10433 CUDA+RPC build
# in /home/dank/llama-cpp-rpc (worktree of /home/dank/llama.cpp).
#
# WARNING: do not name any variable here TEMP, HOST, or GPU_MAX_HEAP_SIZE.
# The ROCm HIP runtime reads those bare env vars (see the 2026-08-13 TEMP
# incident in serverAppConfigs-docs/deployment.md).

# Bind address and port for ggml-rpc-server. Must be the LAN address the head
# can reach; the default bind (127.0.0.1) refuses remote clients.
RPC_BIND=192.168.0.235
RPC_PORT=50052

# Device to expose. CUDA0 = the RTX 3090.
DEVICE=CUDA0

# Threads for the worker's CPU device (server has 8 cores; leave 1 for the OS
# and the running frank-default-small service).
THREADS=7

# 1: enable the local tensor file cache (~/.cache/llama.cpp/rpc/). The head
# streams the 31.5 GB model to the worker on first load; with the cache, later
# loads skip the transfer.
CACHE=1

# Worker binary. Must be the SAME llama.cpp build as the head (b10433 /
# 9b05354ec). Version skew hangs the RPC handshake.
WORKER_BIN=/home/dank/llama-cpp-rpc/build/bin/ggml-rpc-server