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.
51 lines
2.2 KiB
Bash
51 lines
2.2 KiB
Bash
# Tunables for frank-default-small (Qwen3.6-35B-A3B-FP8,
|
||
# qwen3_5_moe hybrid MoE, Dankserver, RTX 3090).
|
||
#
|
||
# Runtime: FreeToken v0.1.2 (edge-native MoE serving engine).
|
||
# Installed via uv into /home/dank/freetoken/.venv (CPython 3.12).
|
||
# FreeToken keeps expert weights in host RAM with an LRU GPU cache;
|
||
# KV is paged with radix prefix sharing. Only the 10 full-attention
|
||
# layers page KV (~20 KiB/token); the 30 GDN layers use constant-size
|
||
# per-sequence state (mamba slot pool).
|
||
#
|
||
# Model: Qwen/Qwen3.6-35B-A3B-FP8 (HuggingFace safetensors, modelopt
|
||
# block-fp8 quant, 128x128 weight_block_size, 35 GB on disk).
|
||
# Architecture: qwen3_5_moe — 40 layers (10 attention + 30 GDN),
|
||
# 256 experts / 8 used, 2 KV heads × 256 dim, full_attention_interval=4.
|
||
#
|
||
# Replaced the llama.cpp Tiel-Coder-35B-A3B (UD-Q6_K_XL) deployment on
|
||
# 2026-09-02. The old serve script and env are in .AGENTTRASH/.
|
||
#
|
||
# Pool sizing: GPU budget (~17.6 GiB after weights + fixed caches) is
|
||
# split MoE-first. MOE_CACHE_SIZE pins resident expert slots; NUM_TOKENS
|
||
# pins the KV pool. At 2048 slots / 453005 tokens the split is ~20%
|
||
# residency (2048/10240) and ~8.6 GiB KV. Live resize via
|
||
# `ft ctl cache --kv N --moe M` can grow KV by shrinking MoE without
|
||
# restart (the reverse requires a restart).
|
||
#
|
||
# 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). This box is NVIDIA/CUDA, but the rule keeps the env portable.
|
||
|
||
# Model directory (safetensors checkpoint, 35 GB).
|
||
MODEL_DIR=/home/dank/models/qwen36-35b-a3b-fp8
|
||
|
||
# FreeToken venv (uv-managed CPython 3.12, ft CLI, flashinfer, torch+cu130).
|
||
FT_VENV=/home/dank/freetoken/.venv
|
||
CUDA_HOME_DIR=/home/dank/freetoken/.venv/lib/python3.12/site-packages/nvidia/cu13
|
||
|
||
ALIAS=frank-default-small
|
||
BIND_ADDR=0.0.0.0
|
||
LISTEN_PORT=7770
|
||
|
||
# Expert residency: 2048 of 10240 total expert instances (20%).
|
||
# Each slot ~3 MiB → ~6.0 GiB VRAM for the MoE cache.
|
||
MOE_CACHE_SIZE=2048
|
||
|
||
# KV pool: 453005 tokens (~8.6 GiB at ~20 KiB/token).
|
||
# Covers 4 concurrent sessions at ~113k unique context each
|
||
# (more with radix prefix sharing for common prefixes).
|
||
NUM_TOKENS=453005
|
||
|
||
# Max concurrent decoding requests (also caps mamba slot allocation).
|
||
MAX_RUNNING_REQUESTS=4 |