#!/usr/bin/env bash
# frank-primary entrypoint: exec the native luce_server with the DeepSeek V4
# launch shape for this host (2x R9700 gfx1201, 246 GiB RAM).
#
# The image's own entrypoint (server/scripts/entrypoint.sh) only forwards a
# fixed Qwen/DFlash flag set and cannot express the DS4 flags, so this unit
# bypasses it (PodmanArgs=--entrypoint) and execs the binary directly. The
# C++ server reads LUCE_* environment variables straight from the process
# environment, so no env plumbing is needed here.
#
# SOURCE BRANCH. The `deepseek41` architecture exists only on the
# `feat/ds41-engine` branch of Luce-Org/lucebox: main carries `deepseek4`
# alone and rejects this checkpoint with "unsupported model architecture
# 'deepseek41'" (server/src/common/backend_plan.cpp). The image is built from
# that branch — see serverAppConfigs-docs/LLM/frank-primary-lucebox-ds41.md.
#
# LAUNCH SHAPE (server/docs/DS41.md — the V4.1 page, not the V4 DS4.md one):
#   --ds4-prefill exact   THE ONLY prefill this placement can run. Any
#                         approximate mode (dense, sparse) makes
#                         DeepSeek4Backend::requires_monolithic_model() true,
#                         and a monolithic load asks ggml for the whole 187 GiB
#                         expert set as ONE device-0 buffer — measured
#                         2026-09-26: "allocating 191932.25 MiB on device 0:
#                         cudaMalloc failed: out of memory", then
#                         "monolithic HIP load required for dense prefill".
#                         DS41.md's dense-prefill section measures that mode
#                         where the experts fit (in-process owners); on a
#                         32 GiB target it cannot. exact feeds the prompt token
#                         by token, which is what the hybrid tier streams for.
#   --chunk 1024          DS41.md's cold-expert chunk. The runtime caps the
#                         chunk to what fits after headroom regardless.
#   --max-ctx 131072      the V4.1 default window. The MLA compressed caches
#                         are F16 by design and stay small; --cache-type-k/v
#                         are ignored by the DeepSeek4 backend, so they are
#                         not passed.
#   --prefix-cache-slots 0 --prefill-cache-slots 0
#                         the DS41.md bring-up recipe (the server default is
#                         32 prefix slots). Lift them once capacity under load
#                         has been measured, not before.
#
# EXPERT PLACEMENT. 377 GiB of weights against 64 GiB of VRAM: only the dense
# weights, the compressed caches and a hot expert stack fit on hip:0, and the
# remaining routed experts are streamed out of the mmapped page cache/NVMe by
# the hybrid expert tier. LUCE_EXPERT_STREAM_DEVICE=1 moves the streamed-
# expert slot cache onto the second R9700 — it defaults to the target device,
# where it would compete with the hot stack. Both the owner stack and the
# slot cache then auto-size to their device's free memory minus the 1.5 GiB
# discrete headroom.
#
# No DSpark draft is published for DeepSeek-V4.1-Flash, so this is plain
# autoregressive decode (no --draft, no LUCE_DS4_SPEC).
set -euo pipefail

MODEL="${FRANK_PRIMARY_MODEL:-/models/DeepSeek-V4.1-Flash/DeepSeek-V4.1-Flash-ROCMFP23.gguf}"
BIN="${FRANK_PRIMARY_BIN:-/opt/lucebox-hub/server/build/luce_server}"

# The second R9700 holds the streamed-expert slot cache and computes them.
export LUCE_EXPERT_STREAM_DEVICE="${LUCE_EXPERT_STREAM_DEVICE:-1}"
# The hot expert stack must be sized EXPLICITLY. Left alone the runtime
# budgets gpu_free - kv - warm - safety (22.35 GiB here), which leaves only
# its 0.50 GiB safety margin free while the fit check then demands the 1.50
# GiB discrete headroom — its own auto-sizing can never pass on a 32 GiB
# target: "device 0 memory: 30.97 of 31.86 GiB used, 0.89 GiB free (headroom
# 1.50 GiB): does not fit". 18000 MB is the value DS41.md measured its R9700
# rows at; it puts ~1500 experts (37/layer) resident and leaves device 0
# ~5 GiB free, so the fit check passes with room for transient buffers.
export LUCE_EXPERT_BUDGET_MB="${LUCE_EXPERT_BUDGET_MB:-18000}"
# rocBLAS/BLAS dispatch and queue depth, as the fleet's other ROCm servers.
export ROCBLAS_USE_HIPBLASLT="${ROCBLAS_USE_HIPBLASLT:-0}"
export GPU_MAX_HW_QUEUES="${GPU_MAX_HW_QUEUES:-8}"

if [[ ! -f "$MODEL" ]]; then
    echo "frank-primary: model missing at $MODEL" >&2
    exit 1
fi
if [[ ! -x "$BIN" ]]; then
    echo "frank-primary: binary missing at $BIN (image build failed?)" >&2
    exit 1
fi

exec "$BIN" "$MODEL" \
    --host 0.0.0.0 \
    --port 7770 \
    --model-name frank-primary \
    --target-device hip:0 \
    --max-ctx 131072 \
    --chunk 1024 \
    --ds4-prefill exact \
    --prefix-cache-slots 0 \
    --prefill-cache-slots 0