Frank
6efb0fb231
Replace the llama.cpp Tiel-Coder-35B-A3B (UD-Q6_K_XL) deployment with FreeToken v0.1.2 — an edge-native MoE serving engine that keeps expert weights in host RAM with an LRU GPU cache and paged KV with radix prefix sharing. Model: Qwen/Qwen3.6-35B-A3B-FP8 (modelopt block-fp8, 128×128 weight_block_size). Architecture: qwen3_5_moe — 40 layers (10 attention + 30 GDN), 256 experts/8 used. Production config: - 2048 MoE cache slots (20% of 10240 expert instances, ~6.0 GiB VRAM) - 453005 KV tokens (~8.6 GiB, ~20 KiB/token for 10 attn layers) - 4 max-running-requests (mamba slot pool: 24 slots) - bs4 decode: ~87 tok/s aggregate, ~30 tok/s bs1 - Prefill: ~1,130 tok/s at 4k prompt Quirk: FreeToken v0.1.2 supports modelopt block-fp8, NVFP4, and per-tensor FP8, but NOT compressed-tensors per-channel FP8 (Huihui/Ornith both failed). Live KV resize via ft ctl cache grows KV by shrinking MoE; reverse needs restart. Old llama.cpp scripts archived to .AGENTTRASH/. Full benchmark sweep (bs1/bs3/bs4/bs6, 8k–700k KV) documented in docs/LLM/freetoken-benchmark-sweep.md.
73 lines
2.5 KiB
Bash
Executable File
73 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Serve Qwen/Qwen3.6-35B-A3B-FP8 as frank-default-small via FreeToken
|
||
# on Dankserver (RTX 3090, 60 GB RAM).
|
||
#
|
||
# Runtime: FreeToken v0.1.2 (edge-native MoE serving engine).
|
||
# - Experts live in host RAM; an LRU cache of expert slots is resident
|
||
# on the GPU. Misses are streamed over PCIe.
|
||
# - Paged KV cache (radix prefix sharing). Only the 10 full-attention
|
||
# layers page KV (~20 KiB/token); the 30 GDN/linear-attention layers
|
||
# hold constant-size per-sequence state (mamba slots).
|
||
# - OpenAI-compatible API (/v1/chat/completions, /v1/models).
|
||
#
|
||
# Model: Qwen/Qwen3.6-35B-A3B-FP8 (safetensors, modelopt block-fp8,
|
||
# 128x128 weight_block_size). Architecture: qwen3_5_moe — 40 layers,
|
||
# full_attention_interval=4 (10 attention + 30 GDN), 256 experts / 8 used,
|
||
# 2 KV heads × 256 dim. 35 GB on disk.
|
||
#
|
||
# Pool sizing: the GPU budget is split MoE-first between expert residency
|
||
# and KV pages. --moe-cache-size pins the number of resident expert
|
||
# slots; --num-tokens pins the KV pool capacity. Live resize is possible
|
||
# via `ft ctl cache --kv N --moe M` (grows KV by shrinking MoE; shrinking
|
||
# KV requires a restart due to the swap-during-rebuild memory cost).
|
||
#
|
||
# Tunables come from frank-default-small.env unless FRANK_SMALL_ENV_FILE
|
||
# overrides that path.
|
||
set -euo pipefail
|
||
|
||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
ENV_FILE="${FRANK_SMALL_ENV_FILE:-$SCRIPT_DIR/frank-default-small.env}"
|
||
if [[ -f "$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/qwen36-35b-a3b-fp8}"
|
||
: "${ALIAS:=frank-default-small}"
|
||
: "${BIND_ADDR:=0.0.0.0}"
|
||
: "${LISTEN_PORT:=7770}"
|
||
: "${FT_VENV:=/home/dank/freetoken/.venv}"
|
||
: "${CUDA_HOME_DIR:=${FT_VENV}/lib/python3.12/site-packages/nvidia/cu13}"
|
||
|
||
# Pool sizing (expert residency vs KV cache tradeoff).
|
||
: "${MOE_CACHE_SIZE:=2048}"
|
||
: "${NUM_TOKENS:=453005}"
|
||
: "${MAX_RUNNING_REQUESTS:=4}"
|
||
|
||
# Paths
|
||
FT_BIN="${FT_VENV}/bin/ft"
|
||
MODEL="${MODEL_DIR}"
|
||
|
||
if [[ ! -x "$FT_BIN" ]]; then
|
||
echo "missing FreeToken CLI: $FT_BIN" >&2
|
||
exit 1
|
||
fi
|
||
if [[ ! -d "$MODEL" ]]; then
|
||
echo "missing model directory: $MODEL" >&2
|
||
exit 1
|
||
fi
|
||
|
||
export PATH="${FT_VENV}/bin:${PATH}"
|
||
export CUDA_HOME="${CUDA_HOME_DIR}"
|
||
|
||
exec "$FT_BIN" serve \
|
||
--model "$MODEL" \
|
||
--served-model-name "$ALIAS" \
|
||
--host "$BIND_ADDR" \
|
||
--port "$LISTEN_PORT" \
|
||
--moe-cache-size "$MOE_CACHE_SIZE" \
|
||
--num-tokens "$NUM_TOKENS" \
|
||
--max-running-requests "$MAX_RUNNING_REQUESTS" |