# 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-default
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].
# 0.40,0.60 = 40% of layers on the 3090 (~26 layers) - the maximum that
# fits its 24 GB card with 2x200700 f16 KV (see the KV math in
# docs/Pipeline Parallelism/Qwen3.8 PP Deployment.md). The 3090 is 2-3x
# faster per layer, so shifting weight to it is also a speed win.
TENSOR_SPLIT=0.40,0.60

# Context pool. 401400 total = 2 parallel slots x 200700 per slot
# (n_ctx_seq = n_ctx / n_seq_max, llama-context.cpp:293).
CTX_SIZE=401400
PARALLEL=2

# 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, unquantized (f16). 16 full-attention layers x 2 (K,V) x 4 heads
# x 256 dim x 2 bytes = 64 KiB/token -> 401400 tokens = 24.5 GiB total.
# Keep K == V so Flash Attention stays enabled.
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16

# 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

# 4 (info): clean journal for interactive use. Raise to 10 only when
# debugging the layer split (the per-layer assignment lines are debug-level).
VERBOSITY=4

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