# Tunables for frank-dragoon (kingjones777/Qwen3.8-Flash-Next-ROCmFP4-
# STRIX-GGUF on the kingjones30/ROCmFPX llama.cpp runtime, Dankclaw,
# Strix Halo gfx1151, unified memory).
#
# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
# qwen4exp-on-rocmfpx-d3ca537 patch applied — the model card's pinned
# runtime: ROCmFP4 tensor types AND the qwen4exp architecture in one
# tree; stock llama.cpp and charlie's fork alone cannot load this GGUF).
# Built per the card recipe:
#   cmake -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release
# at /home/dank/GitPackages/kingjones-ROCmFPX/build.
# Replaced the agentionai ROCmFP4-FAST imatrix deployment (charlie's
# build-qwen38 runtime) on 2026-08-30.
#
# Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
# 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
# at layer 1), Q4_0_ROCMFP4_STRIX (file_type 105), 113.47 GiB single
# file. STRIX is the top quality tier: PLE table at Q8_0 (50.66 GiB),
# token embeddings + lm head at Q6_K. The PLE table NEVER enters GPU
# memory — it streams from the file through the OS page cache. Two hard
# card constraints:
#  1. mmap MUST stay enabled (default) — --no-mmap forces the 50.66 GiB
#     table into anonymous memory and the cgroup killer takes the
#     process with nothing in the server log (only dmesg).
#  2. Do NOT pin the PLE tensor to CPU with -ot — measured gen fell
#     ~23 -> 13.4 tok/s; the kernel streams it better.
# NOTE: the card's own build_attn_qsa still calls ggml_fill on the
# F16-cast kq mask (the path that aborted our charlie build with
# --flash-attn on before scripts/patches/qwen4exp-qsa-f32-mask.patch).
# If a clean kingjones-tree build aborts graph build with
# GGML_ASSERT(a-type == GGML_TYPE_F32), port that fix (F32 base mask +
# cast at the attention call) into this tree and rebuild.
#
# 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.

# kingjones30/ROCmFPX runtime binary (card recipe build).
LLAMA_BIN=/home/dank/GitPackages/kingjones-ROCmFPX/build/bin/llama-server

# Model package from
# https://huggingface.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF
# Layout: single unsharded GGUF, text-only (the repo ships no mmproj;
# the vision tower below is borrowed from the agentionai FAST package —
# same base model, f16 — kept only if it loads clean, drop
# MMPROJ_PATH if it does not).
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX
MODEL_FILE=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf
MMPROJ_PATH=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf

# Qwen-Sharp chat template (tracked in the repo, staged on the host). The
# Sharp template drives thinking on by default (medium effort); the server
# emits reasoning in DeepSeek format so clients receive reasoning_content
# separately instead of literal thinking tags in content.
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'

# Alias + network.
ALIAS=frank-dragoon
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770

# Serving: 401408-token context, TWO slots (parallel 2), batch 4096 /
# ubatch 512, 16+16 threads, f16 KV, 16 context checkpoints, 8 GiB
# prompt cache. --fit off: auto-fit segfaults on this model's
# hyper-connection/indexer config; -ngl 999 puts every layer on the
# SVM-backed GPU pool. ubatch 512 matches the card's re-measurement
# (-ub 1024/2048/4096 showed no effect; -t 32 vs 16 is noise).
#
# CTX_SIZE=401408 / PARALLEL=2: carried over from the FAST deployment
# where it loaded clean (~74 s, health 200). The card measures the full
# 262144 window at ~71.7 GiB GTT at load on the same 128 GB board; QSA
# caps KV growth so the extra window is cheap. KV footprint scales
# with the 12 attention layers only. Verify load on first STRIX boot.
CTX_SIZE=401408
PARALLEL=2

BATCH_SIZE=4096
UBATCH_SIZE=512
NUM_THREADS=16
THREAD_BATCH=16
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16
CTX_CHECKPOINTS=16
CACHE_RAM=8192
SLOT_SAVE_PATH=/home/dank/serverAppConfigs/scripts/slot-state
SPLIT_MODE=none
FIT=off
NGL=999
FLASH_ATTN=on

# Sampling (card instruct table, non-thinking).
TEMPERATURE=0.7
TOP_K=20
TOP_P=0.8
MIN_P=0.0
PRESENCE_PENALTY=1.5

# Reasoning on (Sharp template drives it; preserve_thinking + preserve_reasoning
# keep the reasoning trail in the conversation). DeepSeek format projects the
# reasoning into the API's reasoning_content field instead of literal thinking
# tags.
REASONING=on
REASONING_FORMAT=deepseek

# Strix Halo unified memory + native gfx1151.
HSA_OVERRIDE_GFX_VERSION=11.5.1

VERBOSITY=4


# Speculative decoding: disabled. The card's Usage block ships no spec
# flags. The Flash-Next MTP heads do not load on this loader (requires
# per-layer blk.N.hc_attn_norm; every head carries only blk.48 —
# verified 3x on build-qwen38). DRAFT_MODEL_* point at the retired
# agentionai FAST head and are unused while SPEC_TYPE=none.
DRAFT_MODEL_DIR=/home/dank/models/mtp-Qwen3.8-Flash-Next-FAST
DRAFT_MODEL_FILE=Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST.gguf
SPEC_TYPE=none
SPEC_DRAFT_N_MAX=3
SPEC_DRAFT_N_MIN=0
SPEC_DRAFT_P_MIN=0.75
SPEC_DRAFT_NGL=999
SPEC_DRAFT_DEVICE=ROCm0
SPEC_DRAFT_TYPE_K=f16
SPEC_DRAFT_TYPE_V=f16