Frank
c984a3e4e6
- Remove CACHE_TYPE_K/CACHE_TYPE_V (fp16 default on GPU) - Increase BATCH_SIZE from 2048 to 8192 - Increase UBATCH_SIZE from 512 to 2048 - Remove --cache-type-k and --cache-type-v from llama-server flags
37 lines
1.4 KiB
Bash
37 lines
1.4 KiB
Bash
# Tunables for frank-default-large (HauhauCS Qwen3.6-27B Q8_K_P, DFlash+ngram-mod, dankclaw)
|
|
# Runtime: llama.cpp llama-server; AMD Strix Halo (gfx1151) 96GB UMA; Ryzen AI MAX+ 395.
|
|
MODEL_DIR=/home/dank/models
|
|
ALIAS=frank-default-large
|
|
HOST=0.0.0.0
|
|
PORT=7770
|
|
# 3 parallel slots x 200700 ctx each = 602100 total context pool.
|
|
CTX_SIZE=602100
|
|
PARALLEL=3
|
|
# Spec: DFlash draft model. Bench (4k, ROCm) showed draft-dflash fastest
|
|
# generation (20.2 t/s): DFlash+ngram 16.9, ngram-only 8.7. ngram layering
|
|
# reduced throughput, so it is not layered in production.
|
|
SPEC_TYPE=draft-dflash
|
|
SPEC_DRAFT_N_MAX=8
|
|
SPEC_NGRAM_MOD_N_MIN=48
|
|
SPEC_NGRAM_MOD_N_MAX=64
|
|
SPEC_NGRAM_MOD_N_MATCH=24
|
|
# Backend device from --list-devices. ROCm wins on generation; Vulkan renders
|
|
# DFlash spec unusable (NONE-op abort) and gen is slower on ngram (6.9 t/s).
|
|
DEVICE=ROCm0
|
|
# Dense model (Qwen3.6-27B, not MoE): no MoE CPU offload. Full offload.
|
|
N_GPU_LAYERS=all
|
|
# KV on GPU, fp16 (unquantized). Default ggml_type for both K and V.
|
|
# Batch sizing: fp16 KV is larger than q8_0, but user has verified this
|
|
# configuration fits. See frank-default-large-benchmark.md.
|
|
BATCH_SIZE=8192
|
|
UBATCH_SIZE=2048
|
|
# Sampling settings — per HauhauCS Qwen3.6-27B model card.
|
|
# Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
|
|
# Clients may override per-request; these are the server-side defaults.
|
|
TEMP=1.0
|
|
TOP_K=20
|
|
TOP_P=0.95
|
|
MIN_P=0.0
|
|
THREADS=12
|
|
THREADS_HTTP=1
|