Frank
d9af7f1d19
- Move all previous scripts to old/scripts/ (retired PP/NPU-era) - frank-default-large: llama.cpp FastMTP on dankserver (HauhauCS Qwen3.8-27B IQ4_XS + FastMTP 32K draft + ngram-mod, K q8_0/V f16, 128K ctx, batch 2048/ubatch 1024, port 7770) - frank-default-small: vLLM ROCm on dankclaw (Avesed Qwen3.6-35B-A3B INT8 W8A8, full 262144 ctx, no KV quant, 4 seqs, batch 16384, ngram spec, port 52625) - retarget deploy.sh (dankserver/dankclaw, inline sudo, no helpers) - docs: deployment + index + AGENTS.md + README for new topology, superseded banners on retired docs, add frank-redo-2026-08-17 runbook
41 lines
1.6 KiB
Bash
41 lines
1.6 KiB
Bash
# Tunables for frank-default-small (vLLM, dankclaw, Strix Halo gfx1151).
|
|
#
|
|
# Runtime: vLLM (ROCm) in /home/dank/vllm-venv serving
|
|
# Avesed/Qwen3.6-35B-A3B-INT8-W8A8 (compressed-tensors INT8 W8A8, MoE 35B
|
|
# total / 3B active, Qwen3.5-MoE hybrid: 30 of 40 layers are GatedDeltaNet
|
|
# linear attention). Alias frank-default-small, port 52625.
|
|
#
|
|
# The ROCm vLLM install was created with:
|
|
# uv venv --python /usr/bin/python3.12 /home/dank/vllm-venv
|
|
# uv pip install --python /home/dank/vllm-venv vllm --torch-backend=auto
|
|
# The --torch-backend=auto resolver pulls the AMD ROCm wheels (torch +
|
|
# amd-torch-device-gfx1151 + vllm rocm variant) from the AMD index.
|
|
|
|
VLLM_BIN=/home/dank/vllm-venv/bin/vllm
|
|
MODEL=Avesed/Qwen3.6-35B-A3B-INT8-W8A8
|
|
ALIAS=frank-default-small
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=52625
|
|
|
|
# Full native context. The KV cache stays unquantized (auto = model dtype,
|
|
# bf16). Worst-case KV at 262144 x 4 sequences is ~10.7 GiB; weights are
|
|
# ~35 GiB; total fits the Strix Halo unified pool with room to spare.
|
|
MAX_MODEL_LEN=262144
|
|
KV_CACHE_DTYPE=auto
|
|
|
|
# Concurrency and batching (user request).
|
|
MAX_NUM_SEQS=4
|
|
MAX_NUM_BATCHED_TOKENS=16384
|
|
|
|
# vLLM has no separate ubatch knob. The scheduler issues one batch per step
|
|
# with up to max-num-batched-tokens tokens; the KV cache is preallocated at
|
|
# max-model-len. Set gpu-memory-utilization below 1.0 so the unified pool
|
|
# keeps headroom for the host.
|
|
GPU_MEMORY_UTILIZATION=0.92
|
|
|
|
# ngram speculative decoding (vLLM ngram proposer).
|
|
# prompt_lookup_max = ngram window; num_speculative_tokens = draft depth.
|
|
NGRAM_LOOKUP_MAX=5
|
|
NGRAM_LOOKUP_MIN=1
|
|
NUM_SPEC_TOKENS=5
|