# Tunables for frank-default-large (CIRU llama.cpp, dankclaw, Strix Halo
# gfx1151).
#
# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
# qwen3.8-activefpx-promptforge-v2.3 plus the v3 output-K8 runtime patch
# serving kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4 (dense, Q6 AGENT
# GGUF) with the standalone MTP Q4_0 draft head. Alias frank-default-large,
# port 7770.
#
# This model replaced jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge (v3) on
# 2026-08-24. The new model is a plain ROCmFP4 GGUF (no PromptForge .pfs
# sidecars, no Output-K8 proxy); the requested file is Q6_.

# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The ROCm
# HIP runtime reads those bare env vars (see the 2026-08-13 TEMP incident).
# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.

# CIRU llama-server binary (ROCmFPX v2.3 + v3 output-K8 patch build, built
# against the private TheRock ROCm 7.15 SDK kept in the retired ling3-ciru
# venv). ROCm 7.15 is required for the advertised Strix Halo performance.
LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server

# Model files. Plain dense Qwen3.8-27B ROCmFP4 Q6 AGENT GGUF plus the standalone
# MTP draft head and the vision projector. Kingjones 2026-08-24.
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf
MTP_DRAFT_FILE=mtp-Qwen3.8-27B-Q4_0.gguf
MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf

# Qwen-Sharp chat template (tracked in the repo, staged on the host).
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
# enable_thinking on by default in the Sharp template; medium effort default.
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true}'

# ROCm 7.15 SDK paths (inside the retired ling3-ciru venv).
ROCM_DEVEL=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel
ROCM_LIB=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries
ROCM_CORE=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core

ALIAS=frank-default-large
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770

# Serving: full native 262144 context, 1 slot. f16 KV, context checkpoints,
# prompt cache, draft-mtp with standalone Q4_0 head, n_max 4 (the knee for
# the dense model). Unified memory; rocm-smi reports the 64 GiB budget.
CTX_SIZE=262144
PARALLEL=1
BATCH_SIZE=4096
UBATCH_SIZE=4096
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16
CTX_CHECKPOINTS=16
CACHE_RAM=8192

# Dense-model MTP draft (standalone Q4_0 head, n_max 4). No PromptForge .pfs
# sidecars are loaded; the LLAMA_CPU_ARGMAX fast path stays off.
SPEC_DRAFT_N_MAX=4
SPEC_DRAFT_N_MIN=0
SPEC_DRAFT_P_MIN=0.0
SPEC_DRAFT_P_SPLIT=0.10

# Sampling (kingjones model card / Sharp default).
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95

# Thinking on (Qwen-Sharp template drives thinking on; reasoning format
# projects the tar into reasoning_content).
REASONING=on
REASONING_FORMAT=deepseek

VERBOSITY=4