|
|
|
@@ -1,110 +1,90 @@
|
|
|
|
|
# Tunables for frank-small (ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF, the IQ3_S
|
|
|
|
|
# build with the MTP head, plus the BF16 vision projector) on mainline
|
|
|
|
|
# llama.cpp, Dankclaw's RTX 3090, since 2026-09-16.
|
|
|
|
|
# Tunables for frank-small (HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-
|
|
|
|
|
# Balanced, Q4_K_M, plus the BF16 vision projector and the separate MTP
|
|
|
|
|
# sidecar) on mainline llama.cpp, Dankclaw's RTX 3090, since 2026-09-17.
|
|
|
|
|
#
|
|
|
|
|
# Runtime: llama.cpp master 37b53fd (2026-09-16), CUDA build for sm_86:
|
|
|
|
|
# Runtime: llama.cpp master 37b53fd, CUDA build for sm_86:
|
|
|
|
|
# cmake -B build-cuda -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=ON \
|
|
|
|
|
# -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=86
|
|
|
|
|
# -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=86 -DGGML_CUDA_FA_ALL_QUANTS=ON
|
|
|
|
|
# cmake --build build-cuda --target llama-server -j
|
|
|
|
|
# GGML_CUDA_FA_ALL_QUANTS is deliberately OFF in that build: it is only needed
|
|
|
|
|
# for QUANTIZED KV with flash attention, and this service runs f16 KV (below).
|
|
|
|
|
# GGML_CUDA_FA_ALL_QUANTS is ON: this service runs q8_0 KV with flash
|
|
|
|
|
# attention, and without the flag quantized-KV prefill collapses ~12x on
|
|
|
|
|
# CUDA (see the CUDA lesson in AGENTS.md).
|
|
|
|
|
#
|
|
|
|
|
# Model: ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF, the `-mtp` build of IQ3_S.
|
|
|
|
|
# GSQ-RCO assigns a separate quantization type to every tensor from a
|
|
|
|
|
# gradient-based search under a total size budget, rather than applying one
|
|
|
|
|
# type throughout; IQ3_S at 3.50 bpw is the release's task-lossless operating
|
|
|
|
|
# point (AIME25 100.00 and LiveCodeBench v6 85.71 match BF16 exactly,
|
|
|
|
|
# GPQA-Diamond 0.51 behind, at 11.8 GB against 53.8).
|
|
|
|
|
# Model: HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced at Q4_K_M
|
|
|
|
|
# (6.87 GiB). Architecture (GGUF arch gemma4): 48 layers, MHA with 16 kv
|
|
|
|
|
# heads x 512 head_dim, rope freq_base 1e6, final logit softcapping 30,
|
|
|
|
|
# per-layer token embeddings (PLE) inside the file, and a sliding-window
|
|
|
|
|
# attention pattern (attention.sliding_window = 1024) -- most layers cache
|
|
|
|
|
# only a 1024-position window, which is why the KV pool is a fraction of
|
|
|
|
|
# the full-ctx x all-layers number.
|
|
|
|
|
#
|
|
|
|
|
# WHY THAT FILE: the `-mtp` build is ~0.35 GB larger because it carries the
|
|
|
|
|
# model's Multi-Token Prediction head as GGUF block `blk.64.nextn.*`
|
|
|
|
|
# (qwen35.nextn_predict_layers = 1). llama.cpp loads it from the SAME file --
|
|
|
|
|
# `--spec-type draft-mtp` sets load_mtp, and the draft context runs on the main
|
|
|
|
|
# model's weights (common/common.cpp passes shares_model when there is no
|
|
|
|
|
# --model-draft; speculative.cpp gives it LLAMA_CONTEXT_TYPE_MTP), so there is
|
|
|
|
|
# no second 12 GB copy in VRAM. MTP is therefore a property of the FILE, not of
|
|
|
|
|
# the flags: the plain IQ3_S build has no MTP tensors to load.
|
|
|
|
|
# MTP: the Multi-Token Prediction head ships as a SEPARATE file
|
|
|
|
|
# (mtp-gemma-4-12B-it.gguf, arch gemma4-assistant, 4 nextn layers, 0.24
|
|
|
|
|
# GiB). Unlike the Qwen3.8 -mtp build (head inside the main file), this one
|
|
|
|
|
# is passed via --model-draft with --spec-type draft-mtp, so the draft
|
|
|
|
|
# context loads the assistant model. The same --spec-type value chains the
|
|
|
|
|
# draftless ngram-mod matcher, which attaches unconditionally; two
|
|
|
|
|
# context-backed drafters cannot share one process, so draft-mtp,ngram-mod
|
|
|
|
|
# is the only legal shape that carries both.
|
|
|
|
|
#
|
|
|
|
|
# Architecture (GGUF arch qwen35): 64 layers laid out as 16 x (3 x (Gated
|
|
|
|
|
# DeltaNet -> FFN) + 1 x (Gated Attention -> FFN)) -- 48 linear-attention
|
|
|
|
|
# layers with CONSTANT-SIZE per-sequence state and 16 full-attention layers,
|
|
|
|
|
# 4 KV heads x 256 head_dim. Only the attention layers take KV, so a token
|
|
|
|
|
# costs 2 (K,V) x 4 heads x 256 x 2 B = 64 KiB at f16 (34 KiB at q8_0, 18 KiB
|
|
|
|
|
# at q4_0), and the DeltaNet layers add ~0.16 GiB per sequence in f32 at any
|
|
|
|
|
# depth.
|
|
|
|
|
# SIZING (RTX 3090, 24576 MiB): not modelled by hand -- CTX_SIZE is left
|
|
|
|
|
# unset and --fit sizes the KV pool (q8_0 K and V) against what the 6.87
|
|
|
|
|
# GiB of weights, the 0.16 GiB projector, the MTP sidecar's draft context
|
|
|
|
|
# and the compute buffers leave on the card. The engine prints the chosen
|
|
|
|
|
# context at startup; read it from the log, do not hard-code it back here.
|
|
|
|
|
#
|
|
|
|
|
# SIZING (RTX 3090, 24576 MiB) -- modelled, and the loader's own ledger
|
|
|
|
|
# ("KV self size", "compute buffer size") outranks it:
|
|
|
|
|
# weights 11.29 GiB (12,120,016,960 B)
|
|
|
|
|
# mmproj 0.87 GiB (931,146,528 B, 27 blocks)
|
|
|
|
|
# MTP draft KV 0.50 GiB (its context is n_ctx long
|
|
|
|
|
# over one nextn layer: 4 KiB/token)
|
|
|
|
|
# DeltaNet state 0.16 GiB (one sequence)
|
|
|
|
|
# CUDA context + prefill/decode bufs ~1.5 GiB
|
|
|
|
|
# KV at CTX_SIZE 8.00 GiB (131,072 x 64 KiB)
|
|
|
|
|
# --------
|
|
|
|
|
# ~22.3 GiB of 24, ~2 GiB of slack
|
|
|
|
|
# The binding number is the KV: ~9.5 GiB is left after the fixed terms, which
|
|
|
|
|
# at 64 KiB/token is ~155k tokens across all slots. The deployed shape is one
|
|
|
|
|
# slot at 131,072, full f16 precision, no KV quantization risk, no rebuild.
|
|
|
|
|
# Alternatives inside the same budget: 2 x 65536 at f16; 4 x 65536 or
|
|
|
|
|
# 1 x 262144 at q8_0, both of which need a rebuild with
|
|
|
|
|
# -DGGML_CUDA_FA_ALL_QUANTS=ON (without it quantized-KV prefill collapses
|
|
|
|
|
# ~12x on CUDA -- see the CUDA lesson in AGENTS.md).
|
|
|
|
|
# --parallel N DIVIDES --ctx-size between slots; it does not multiply. One slot
|
|
|
|
|
# means a second concurrent request queues behind the first.
|
|
|
|
|
# Vision: --mmproj loads the BF16 projector (11 tensors, 52M params; it
|
|
|
|
|
# also carries an audio encoder, unused by the fleet). The fleet's image
|
|
|
|
|
# path lives here, which is why halogen no longer sets HALOGEN_VISION_TOWER.
|
|
|
|
|
#
|
|
|
|
|
# Sampling: greedy by default, which is the fleet contract (a request that
|
|
|
|
|
# sends no temperature decodes greedy; a client that sends one gets its own).
|
|
|
|
|
# Qwen's own agentic evaluations used temperature 1.0 / top_p 0.95, and the
|
|
|
|
|
# harness applies exactly that per model in models.yml (extraBody), the same
|
|
|
|
|
# way it did for the earlier frank-large runtime.
|
|
|
|
|
# Sampling: greedy by default (the fleet contract); a client that sends a
|
|
|
|
|
# temperature gets its own, and the harness applies per-model overrides
|
|
|
|
|
# from models.yml.
|
|
|
|
|
#
|
|
|
|
|
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE (HIP reads
|
|
|
|
|
# those bare vars on the ROCm hosts -- see the 2026-08-13 incident in
|
|
|
|
|
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE (HIP
|
|
|
|
|
# reads those bare vars on the ROCm hosts -- see the 2026-08-13 incident in
|
|
|
|
|
# AGENTS.md). This box is CUDA, but the rule keeps env files portable.
|
|
|
|
|
|
|
|
|
|
# llama.cpp runtime binary: mainline master 37b53fd, CUDA sm_86.
|
|
|
|
|
# llama.cpp runtime binary: mainline master 37b53fd, CUDA sm_86,
|
|
|
|
|
# FA_ALL_QUANTS=ON.
|
|
|
|
|
LLAMA_BIN=/home/dank/GitPackages/llama.cpp-mainline/build-cuda/bin/llama-server
|
|
|
|
|
|
|
|
|
|
# Model package. The -mtp file is required for speculative decoding.
|
|
|
|
|
MODEL_DIR=/home/dank/models/Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp
|
|
|
|
|
MODEL_FILE=Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf
|
|
|
|
|
MMPROJ_PATH=/home/dank/models/Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp/mmproj-Qwen3.8-27B-BF16.gguf
|
|
|
|
|
# Model package. The MTP sidecar file is required for speculative decoding.
|
|
|
|
|
MODEL_DIR=/home/dank/models/Gemma4-12B-QAT
|
|
|
|
|
MODEL_FILE=Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf
|
|
|
|
|
MMPROJ_PATH=/home/dank/models/Gemma4-12B-QAT/mmproj-Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf
|
|
|
|
|
DRAFT_FILE=mtp-gemma-4-12B-it.gguf
|
|
|
|
|
|
|
|
|
|
# Fleet identity and network. 7771 is this service's own endpoint on Dankclaw;
|
|
|
|
|
# 7770 stays frank-large's. The alias is the id at /v1/models and what clients
|
|
|
|
|
# ask for -- the harness entry in models.yml names it.
|
|
|
|
|
# Fleet identity and network. 7771 is this service's own endpoint on
|
|
|
|
|
# Dankclaw; 7770 stays frank-large's. The alias is the id at /v1/models and
|
|
|
|
|
# what clients ask for -- the harness entry in models.yml names it.
|
|
|
|
|
ALIAS=frank-small
|
|
|
|
|
BIND_ADDR=0.0.0.0
|
|
|
|
|
LISTEN_PORT=7771
|
|
|
|
|
|
|
|
|
|
# One slot at 131,072 tokens with f16 KV (see the sizing note above).
|
|
|
|
|
CTX_SIZE=131072
|
|
|
|
|
# Context: intentionally unset -- --fit decides it (see the sizing note).
|
|
|
|
|
# One slot; a second concurrent request queues behind the first.
|
|
|
|
|
PARALLEL=1
|
|
|
|
|
CACHE_TYPE_K=f16
|
|
|
|
|
CACHE_TYPE_V=f16
|
|
|
|
|
CACHE_TYPE_K=q8_0
|
|
|
|
|
CACHE_TYPE_V=q8_0
|
|
|
|
|
|
|
|
|
|
# Batch geometry: llama.cpp's own defaults (2048 logical / 512 physical). The
|
|
|
|
|
# prefill wall clock at this model size is set by the card, not by ubatch, and
|
|
|
|
|
# the small ubatch keeps the DeltaNet chunk buffers small. Raise UBATCH_SIZE
|
|
|
|
|
# only after reading the compute buffer size the loader reports.
|
|
|
|
|
# Batch geometry: llama.cpp's own defaults (2048 logical / 512 physical).
|
|
|
|
|
BATCH_SIZE=2048
|
|
|
|
|
UBATCH_SIZE=512
|
|
|
|
|
|
|
|
|
|
# CPU threads: this service runs entirely on the GPU (NGL=999), so threads
|
|
|
|
|
# cover tokenization, sampling and the HTTP layer only. Deliberately modest --
|
|
|
|
|
# this host's CPU is shared with halogen's engine, which is CPU-hungry.
|
|
|
|
|
# cover tokenization, sampling and the HTTP layer only. Deliberately modest
|
|
|
|
|
# -- this host's CPU is shared with halogen's engine, which is CPU-hungry.
|
|
|
|
|
NUM_THREADS=8
|
|
|
|
|
THREAD_BATCH=8
|
|
|
|
|
|
|
|
|
|
# Every layer on the 3090, with flash attention.
|
|
|
|
|
# Every layer on the 3090, with flash attention (required for q8 KV).
|
|
|
|
|
NGL=999
|
|
|
|
|
FLASH_ATTN=on
|
|
|
|
|
|
|
|
|
|
# Speculative decoding from the model's own MTP head (see the model note).
|
|
|
|
|
# Draft depth stays llama.cpp's default of 3 tokens.
|
|
|
|
|
SPEC_TYPE=draft-mtp
|
|
|
|
|
# Speculative decoding: the MTP sidecar (draft context) chained with the
|
|
|
|
|
# draftless ngram-mod matcher. Draft depth stays llama.cpp's default of 3.
|
|
|
|
|
SPEC_TYPE=draft-mtp,ngram-mod
|
|
|
|
|
|
|
|
|
|
# Greedy default (fleet contract); reasoning is extracted into
|
|
|
|
|
# reasoning_content with an unlimited budget (the model decides).
|
|
|
|
|
Frank