Frank
215d74f6ce
Dankserver (frank-default-small): - Stock llama.cpp (latest master, CUDA build) replaces ik_llama.cpp - Model: peculiar-ragdoll/Tiel-Coder-35B-A3B UD-Q6_K_XL (30 GB) Architecture: qwen35moe, 40 layers (10 attn + 30 SSM), 256 experts/8 used - CTX_SIZE=200700 (66900/slot × 3 parallel), Q8_0 KV (~2 GB cache buffer) - --cpu-moe for expert offload, -ngl 999 (non-expert on GPU) - mmap enabled; removed ik_llama-specific flags Dankclaw (frank-default-large): - ROCmFPX fork with PR #27742 (qwen4exp arch) merged and built at /home/dank/GitPackages/ROCmFPX/build-qwen38 - Model: kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN (98.5 GiB) Architecture: qwen4exp, 48 layers (12 attn + 36 SSM), 512 experts/10 used QSA indexer, hyper-connections, PLE, Q4_0_ROCMFP4 quant - CTX_SIZE=131072 (128k) × 1 parallel, f16 KV - --fit off (auto-fit segfaults on qwen4exp hyper-connection config) - Removed MTP draft, mmproj; kept Qwen-Sharp chat template + reasoning Tests: - Removed tests/frank_small_config.bats and tests/frank_large_config.bats (moved to .AGENTTRASH/). These were config-assertion tests that checked 'is variable X set to Y' rather than testing the serve script's actual behavior. All 199 remaining tests pass. - Updated test-changed.sh mappings and changed_tests.bats to reflect the removal.
120 lines
4.2 KiB
Bash
Executable File
120 lines
4.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN as
|
||
# frank-default-large via the charlie12345/ROCmFPX llama.cpp fork with
|
||
# PR #27742 (qwen4exp architecture) merged, on Dankclaw (Strix Halo
|
||
# gfx1151, unified memory).
|
||
#
|
||
# Runtime: ROCmFPX llama.cpp built at
|
||
# /home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server
|
||
# with -DGGML_HIP=ON -DGGML_HIP_ROCMI4_W4A4=ON
|
||
# -DCMAKE_HIP_ARCHITECTURES=gfx1151 -DLLAMA_BUILD_WEBUI=OFF.
|
||
#
|
||
# Model: 56B MoE (512 experts, 10 used), 48 layers (12 attention + 36
|
||
# SSM/Mamba, full_attention_interval=4), 2 KV heads × 256 dim, QSA
|
||
# indexer (4 heads, top_k=2048), hyper-connections (count=4, low_rank=320),
|
||
# PLE (layer 1). Q4_0_ROCMFP4_STRIX_LEAN quant, 98.5 GiB, 3-part split.
|
||
#
|
||
# Context: 131072 (128k) × 1 slot. f16 KV cache. Model is loaded with
|
||
# mmap (default) — the 98.5 GiB file is memory-mapped; the Strix Halo
|
||
# unified memory (116 GiB SVM-backed) provides the GPU address space.
|
||
# --fit off is set because the auto-fit code segfaults on this model's
|
||
# hyper-connection/indexer configuration; -ngl 999 places all layers on
|
||
# the GPU (SVM-backed), which the unified memory pool handles.
|
||
#
|
||
# The Qwen-Sharp chat template (scripts/chat-template.jinja) is applied at
|
||
# runtime so the model emits reasoning in DeepSeek format; the reasoning
|
||
# trail is preserved across turns via CHAT_TEMPLATE_KWARGS.
|
||
set -euo pipefail
|
||
|
||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
|
||
if [[ -f "$ENV_FILE" ]]; then
|
||
set -a
|
||
# shellcheck disable=SC1090
|
||
source "$ENV_FILE"
|
||
set +a
|
||
fi
|
||
|
||
# --- defaults (used when the env file does not set them) -------------------
|
||
: "${LLAMA_BIN:=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server}"
|
||
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN}"
|
||
: "${MODEL_FILE:=Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-00001-of-00003.gguf}"
|
||
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
|
||
: "${CHAT_TEMPLATE_KWARGS:={}}"
|
||
: "${ALIAS:=frank-default-large}"
|
||
: "${BIND_ADDR:=0.0.0.0}"
|
||
: "${LISTEN_PORT:=7770}"
|
||
: "${CTX_SIZE:=131072}"
|
||
: "${PARALLEL:=1}"
|
||
: "${BATCH_SIZE:=4096}"
|
||
: "${UBATCH_SIZE:=4096}"
|
||
: "${NUM_THREADS:=16}"
|
||
: "${THREAD_BATCH:=32}"
|
||
: "${CACHE_TYPE_K:=f16}"
|
||
: "${CACHE_TYPE_V:=f16}"
|
||
: "${CTX_CHECKPOINTS:=16}"
|
||
: "${CACHE_RAM:=8192}"
|
||
: "${FIT:=off}"
|
||
: "${TEMPERATURE:=0.7}"
|
||
: "${TOP_K:=20}"
|
||
: "${TOP_P:=0.8}"
|
||
: "${MIN_P:=0.0}"
|
||
: "${PRESENCE_PENALTY:=1.5}"
|
||
: "${REASONING:=on}"
|
||
: "${REASONING_FORMAT:=deepseek}"
|
||
: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
|
||
|
||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||
for f in "$LLAMA_BIN" "$MODEL" "$CHAT_TEMPLATE_FILE"; do
|
||
if [[ ! -r "$f" ]]; then
|
||
echo "missing or unreadable required artifact: $f" >&2
|
||
exit 1
|
||
fi
|
||
done
|
||
if [[ ! -x "$LLAMA_BIN" ]]; then
|
||
echo "missing executable runtime: $LLAMA_BIN" >&2
|
||
exit 1
|
||
fi
|
||
|
||
SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
|
||
ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
|
||
LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
|
||
|
||
exec /usr/bin/env \
|
||
ROCM_PATH="$ROCM_PATH" \
|
||
HIP_VISIBLE_DEVICES=0 \
|
||
LD_LIBRARY_PATH="$LIBRARY_PATH" \
|
||
HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
|
||
"$LLAMA_BIN" \
|
||
--model "$MODEL" \
|
||
--alias "$ALIAS" \
|
||
--chat-template-file "$CHAT_TEMPLATE_FILE" \
|
||
--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
|
||
--host "$BIND_ADDR" \
|
||
--port "$LISTEN_PORT" \
|
||
--jinja \
|
||
--device ROCm0 \
|
||
--gpu-layers 999 \
|
||
--parallel "$PARALLEL" \
|
||
--ctx-size "$CTX_SIZE" \
|
||
--batch-size "$BATCH_SIZE" \
|
||
--ubatch-size "$UBATCH_SIZE" \
|
||
--fit "$FIT" \
|
||
--flash-attn on \
|
||
--cache-type-k "$CACHE_TYPE_K" \
|
||
--cache-type-v "$CACHE_TYPE_V" \
|
||
--threads "$NUM_THREADS" \
|
||
--threads-batch "$THREAD_BATCH" \
|
||
--ctx-checkpoints "$CTX_CHECKPOINTS" \
|
||
--cache-ram "$CACHE_RAM" \
|
||
--cache-prompt \
|
||
--cache-idle-slots \
|
||
--metrics \
|
||
--temp "$TEMPERATURE" \
|
||
--top-p "$TOP_P" \
|
||
--top-k "$TOP_K" \
|
||
--min-p "$MIN_P" \
|
||
--presence-penalty "$PRESENCE_PENALTY" \
|
||
--reasoning "$REASONING" \
|
||
--reasoning-format "$REASONING_FORMAT" \
|
||
--reasoning-budget -1 |