# Head tunables — Qwen3.8-27B pipeline-parallel head (Dankclaw).
#
# The head is the LOCAL side of the split. It runs llama-server (b10433,
# HIP+Vulkan+RPC build in /home/dank/llama.cpp/build) with --rpc pointing at
# the worker on Dankserver. The model file lives on this machine only; the
# worker receives its tensor share over the network at load time.
#
# CRITICAL: this script must NOT pass --device. When --device is set,
# llama.cpp uses exactly that device list and silently drops the RPC device
# (src/llama.cpp llama_prepare_model_devices). Default device selection
# inserts RPC servers at the FRONT of the device list, so the split becomes
# [RPC0, iGPU] and --tensor-split index 0 is the worker.
#
# WARNING: do not name any variable here TEMP, HOST, or GPU_MAX_HEAP_SIZE
# (HIP runtime collision, see the 2026-08-13 TEMP incident).

MODEL_DIR=/home/dank/models
MODEL_FILE=Qwen3.8-27B-UD-Q8_K_XL.gguf
HEAD_BIN=/home/dank/llama.cpp/build/bin/llama-server
ALIAS=frank-pp-large
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770

# Comma-separated RPC endpoints (host:port). One worker here.
RPC_SERVERS=192.168.0.235:50052

# Model split fractions, one per device in order [RPC0, iGPU].
# 1,1 = 50/50: the 3090 gets the first ~32 layers, the Strix the rest.
# Leave empty for the default proportional-to-free-memory split; note the
# Strix reports ~96 GiB (GTT ceiling) vs the 3090's ~24 GB, so the default
# lands around 20% of layers on the 3090 and 80% on the Strix.
TENSOR_SPLIT=1,1

# Context pool. 131072 single slot keeps the KV small (~4.5 GB total at
# q8_0) on both sides; raise for high-context tests (see docs).
CTX_SIZE=131072
PARALLEL=1

# Speculative decoding. Matches production frank-default-large: MTP (bundled
# head, n_max 4 per the published tuning curve) with the ngram-mod fallback.
# Set SPEC_NONE=1 for a raw baseline with no speculation.
SPEC_NONE=0
SPEC_DEFAULT=1
MTP=1
SPEC_DRAFT_N_MAX=4
# Optional standalone MTP draft head (e.g. the Q4_0 ggml-org file). When set,
# it replaces the bundled in-model head via --spec-draft-model.
SPEC_DRAFT_MODEL=
SPEC_NGRAM_MOD_N_MIN=48
SPEC_NGRAM_MOD_N_MAX=64
SPEC_NGRAM_MOD_N_MATCH=24

# KV on GPU, quantized. Keep K == V so Flash Attention stays enabled.
CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0

# Batch sizing: production-verified values (2026-08-14).
BATCH_SIZE=8192
UBATCH_SIZE=256

# Sampling — Qwen3.8 thinking-mode defaults.
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95
MIN_P=0.0

THREADS=12
THREADS_HTTP=1

# 10 (debug): prints per-layer device assignment so the split is verifiable
# in the log. Drop to 4 for quiet production use.
VERBOSITY=10

# 1: --direct-io model load. Required in practice for large models loaded
# over RPC (load hangs otherwise; visorcraft Strix RPC finding).
DIRECT_IO=1