Frank
75bb9bb53e
Found: large ubatch (512) collapses MTP acceptance to ~25% (gen ~9 t/s); ubatch 128 with batch>=2048 triggers premature instant-EOS under 2 concurrent slots. ubatch 256 = ~30 t/s gen, concurrent-safe, ~330 t/s prefill.
58 lines
2.5 KiB
Bash
58 lines
2.5 KiB
Bash
# Tunables for frank-default-large (unsloth Qwen3.8-27B UD-Q8_K_XL, dankclaw)
|
|
# Runtime: llama.cpp llama-server (b10433+, rebuilt 2026-08-14 for bundled-MTP
|
|
# support); AMD Strix Halo (gfx1151) 96GB UMA; Ryzen AI MAX+ 395.
|
|
MODEL_DIR=/home/dank/models
|
|
MODEL_FILE=Qwen3.8-27B-UD-Q8_K_XL.gguf
|
|
ALIAS=frank-default-large
|
|
HOST=0.0.0.0
|
|
PORT=7770
|
|
# Context pool. Qwen3.8 native context = 262144 per sequence.
|
|
# 524288 total / PARALLEL 2 = 262144 per slot, matching the pi client's
|
|
# contextWindow=262144 for frank-default-large. Model is 29GB; ROCm has
|
|
# ~70GB headroom, so 2x262k quantized KV fits. Verify at startup.
|
|
CTX_SIZE=524288
|
|
PARALLEL=2
|
|
# Spec: selected from the 2026-08-14 matrix (bench-spec-matrix.sh).
|
|
# WINNER: draft-mtp alone, n_max=10, p_min off -> ~30 t/s, STABLE, no
|
|
# premature stop. Layered draft-mtp,ngram-mod was faster on paper (median
|
|
# 133 t/s) but is non-deterministic (10-148 t/s) and shows a degenerate
|
|
# instant-EOS (tok=0) -> the same premature-stop class that retired DFlash.
|
|
# Rejected as production-unsafe.
|
|
SPEC_TYPE=draft-mtp
|
|
# Bundled MTP: Qwen3.8 keeps the MTP head in the target GGUF. llama.cpp
|
|
# auto-detects it (b10411+). DRAFT_FILE MUST stay EMPTY.
|
|
DRAFT_FILE=
|
|
# Draft length + sampling floor, from the spec matrix (n_max 2..10, p_min
|
|
# off/0.8; p_min 0.8 did not help draft-mtp and slowed it slightly).
|
|
SPEC_DRAFT_N_MAX=10
|
|
SPEC_DRAFT_P_MIN=
|
|
SPEC_NGRAM_MOD_N_MIN=48
|
|
SPEC_NGRAM_MOD_N_MAX=64
|
|
SPEC_NGRAM_MOD_N_MATCH=24
|
|
# Backend device from --list-devices. ROCm0 is the production backend.
|
|
DEVICE=ROCm0
|
|
# Dense model: full offload. (Not MoE.)
|
|
N_GPU_LAYERS=all
|
|
# KV on GPU, quantized (K q8_0, V q8_0). Keep K == V for Flash Attention;
|
|
# mixed types silently disable FA (long-context decode collapses).
|
|
CACHE_TYPE_K=q8_0
|
|
CACHE_TYPE_V=q8_0
|
|
# Batch sizing (verified 2026-08-14 on Qwen3.8 UD-Q8_K_XL):
|
|
# ubatch 128 with batch>=2048 -> premature-EOS under concurrency (unsafe).
|
|
# ubatch 512 -> MTP acceptance collapses (~25%) -> gen ~9 t/s (slow).
|
|
# ubatch 256 -> ~30 t/s gen, concurrent-safe, ~330 t/s prefill. WINNER.
|
|
# batch 8192 keeps single-shot prefill flexibility; ubatch drives the graph.
|
|
BATCH_SIZE=8192
|
|
UBATCH_SIZE=256
|
|
# Sampling settings — per Qwen3.8-27B model card thinking mode.
|
|
# Thinking: temp=1.0, top_p=0.95, top_k=20, min_p=0. Clients may override.
|
|
# WARNING: do not name this variable TEMP. The ROCm HIP runtime reads the
|
|
# TEMP environment variable (JIT kernel-cache dir); TEMP=1.0 made the HIP
|
|
# runtime SEGV during model load on Aug 13 2026.
|
|
TEMPERATURE=1.0
|
|
TOP_K=20
|
|
TOP_P=0.95
|
|
MIN_P=0.0
|
|
THREADS=12
|
|
THREADS_HTTP=1
|