Frank
57b0be037c
- rebuild llama.cpp stock to b10433 (9b05354ec) for bundled-MTP support - MODEL_FILE -> Qwen3.8-27B-UD-Q8_K_XL.gguf; DRAFT_FILE empty (MTP bundled) - SPEC: draft-mtp, n_max=10, p_min off (~30 t/s stable) - matrix winner - CTX 524288 / parallel 2 = 262144/slot (matches pi contextWindow) - serve script: bundled-MTP (no --spec-draft-model), optional --spec-draft-p-min
95 lines
2.8 KiB
Bash
Executable File
95 lines
2.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Serve unsloth Qwen3.8-27B UD-Q8_K_XL on dankclaw with bundled-MTP
|
|
# speculative decoding (draft-mtp). ROCm backend.
|
|
# Runtime: llama.cpp llama-server (>= b10411).
|
|
#
|
|
# Tunables come from frank-default-large.env in this directory unless the
|
|
# FRANK_LARGE_ENV_FILE environment variable overrides that path.
|
|
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 "$ENV_FILE"
|
|
set +a
|
|
fi
|
|
|
|
# --- defaults (used when the env file does not set them) -----------------
|
|
: "${MODEL_DIR:=/home/dank/models}"
|
|
: "${MODEL_FILE:=Qwen3.8-27B-UD-Q8_K_XL.gguf}"
|
|
: "${DRAFT_FILE:=}" # empty: Qwen3.8 bundles its MTP drafter in-model
|
|
: "${ALIAS:=frank-default-large}"
|
|
: "${HOST:=0.0.0.0}"
|
|
: "${PORT:=7770}"
|
|
: "${CTX_SIZE:=262144}" # Qwen3.8 native context (env may raise for parallel≥2)
|
|
: "${PARALLEL:=2}"
|
|
: "${SPEC_TYPE:=draft-mtp}"
|
|
: "${SPEC_DRAFT_N_MAX:=10}"
|
|
: "${SPEC_NGRAM_MOD_N_MIN:=48}"
|
|
: "${SPEC_NGRAM_MOD_N_MAX:=64}"
|
|
: "${SPEC_NGRAM_MOD_N_MATCH:=24}"
|
|
: "${DEVICE:=ROCm0}"
|
|
: "${N_GPU_LAYERS:=all}"
|
|
: "${CACHE_TYPE_K:=q8_0}"
|
|
: "${CACHE_TYPE_V:=q8_0}"
|
|
: "${BATCH_SIZE:=8192}"
|
|
: "${UBATCH_SIZE:=2048}"
|
|
: "${TEMPERATURE:=1.0}"
|
|
: "${TOP_K:=20}"
|
|
: "${TOP_P:=0.95}"
|
|
: "${MIN_P:=0.0}"
|
|
: "${THREADS:=12}"
|
|
: "${THREADS_HTTP:=1}"
|
|
|
|
LLAMA_SERVER="${LLAMA_SERVER:-/home/dank/llama.cpp/build/bin/llama-server}"
|
|
MODEL="$MODEL_DIR/$MODEL_FILE"
|
|
DRAFT="$MODEL_DIR/$DRAFT_FILE"
|
|
|
|
if [[ ! -f "$MODEL" ]]; then
|
|
echo "missing required file: $MODEL" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Draft-model flag applies only when a separate draft file is provided.
|
|
# Qwen3.8 bundles MTP in-model; leave DRAFT_FILE empty to use bundled MTP.
|
|
SPEC_ARGS=()
|
|
if [[ -n "$DRAFT_FILE" ]]; then
|
|
if [[ ! -f "$DRAFT" ]]; then
|
|
echo "missing required file: $DRAFT" >&2
|
|
exit 1
|
|
fi
|
|
SPEC_ARGS+=(--spec-draft-model "$DRAFT")
|
|
fi
|
|
if [[ -n "${SPEC_DRAFT_P_MIN:-}" ]]; then
|
|
SPEC_ARGS+=(--spec-draft-p-min "$SPEC_DRAFT_P_MIN")
|
|
fi
|
|
|
|
exec "$LLAMA_SERVER" \
|
|
--model "$MODEL" \
|
|
"${SPEC_ARGS[@]}" \
|
|
--spec-type "$SPEC_TYPE" \
|
|
--spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
|
|
--spec-ngram-mod-n-min "$SPEC_NGRAM_MOD_N_MIN" \
|
|
--spec-ngram-mod-n-max "$SPEC_NGRAM_MOD_N_MAX" \
|
|
--spec-ngram-mod-n-match "$SPEC_NGRAM_MOD_N_MATCH" \
|
|
--device "$DEVICE" \
|
|
--gpu-layers "$N_GPU_LAYERS" \
|
|
--fit off \
|
|
--cache-type-k "$CACHE_TYPE_K" \
|
|
--cache-type-v "$CACHE_TYPE_V" \
|
|
--ctx-size "$CTX_SIZE" \
|
|
--parallel "$PARALLEL" \
|
|
--batch-size "$BATCH_SIZE" \
|
|
--ubatch-size "$UBATCH_SIZE" \
|
|
--temp "$TEMPERATURE" \
|
|
--top-k "$TOP_K" \
|
|
--top-p "$TOP_P" \
|
|
--min-p "$MIN_P" \
|
|
--threads "$THREADS" \
|
|
--threads-http "$THREADS_HTTP" \
|
|
--alias "$ALIAS" \
|
|
--host "$HOST" \
|
|
--port "$PORT"
|