frank-small: SGLang MiMo-V2.6-Distill-Qwen-9B INT8 (qwen3_5 hybrid, RTX 3090)

Replaces llama.cpp Gemma4-12B-QAT (payload + binary retained as rollback).
SGLang in a self-contained python3.12 venv with an extracted CUDA 13.0
nvcc toolchain for the sgl-kernel/flashinfer JIT.

Shape: fp8 KV, pinned 606,208-token pool / 4 x 151,552 slots, bf16 mamba
states pinned at 32 slots (the engine autofills the ssm pool to a fixed
~5.1 GB regardless of dtype), eager prefill (no headroom for graph
capture), no spec decode (the checkpoint ships no mtp.* tensors despite
mtp_num_hidden_layers=1 — NEXTN drafts with an uninitialised 4.24 GiB
ghost at 0% acceptance).

Verified: 83.9 tok/s decode, 170k single prompt, 4 concurrent 54k
requests, vision (in-checkpoint tower), reasoning_content field.

scripts/deploy-remote.sh

@@ -1177,23 +1177,39 @@ deploy_llm_large() {
     wait_for_health frank-large http://127.0.0.1:7770/health 1200
 }
 
-# deploy_llm_small — frank-small is mainline llama.cpp on the RTX 3090, as a
-# ROOT unit: the runtime is a native CUDA binary, so there is no container
-# image to install and no generated unit to avoid. relink_unit points
-# /etc/systemd/system/frank-small.service at the repo file and boot persistence
-# is that unit's [Install] section.
+# deploy_llm_small — frank-small is SGLang (python3.12 venv) on the RTX 3090,
+# as a ROOT unit: the runtime is a self-contained venv, so there is no
+# container image to install and no generated unit to avoid. relink_unit
+# points /etc/systemd/system/frank-small.service at the repo file and boot
+# persistence is that unit's [Install] section.
 #
 # It is a SEPARATE endpoint on port 7771; frank-large keeps 7770. The 3090 is
 # not shared: frank-large's engine runs on the gfx1151 iGPU.
-LLM_SMALL_MODEL="${LLM_SMALL_MODEL:-/home/dank/models/Gemma4-12B-QAT/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf}"
+LLM_SMALL_MODEL_DIR="${LLM_SMALL_MODEL_DIR:-/home/dank/models/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound}"
+LLM_SMALL_RUNTIME="${LLM_SMALL_RUNTIME:-/home/dank/GitPackages/sglang-cu128/bin/sglang}"
 
 deploy_llm_small() {
-    if [[ ! -f "$LLM_SMALL_MODEL" ]]; then
-        echo "ERROR: model absent at $LLM_SMALL_MODEL" >&2
-        echo "frank-small: fetch HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced (Q4_K_M, the mmproj and the MTP sidecar) first;" >&2
+    # Refuse rather than restart-loop: a unit whose runtime or payload is
+    # missing never becomes healthy, and a green deploy would leave the
+    # endpoint dark with nothing in the log to say why.
+    if [[ ! -x "$LLM_SMALL_RUNTIME" ]]; then
+        echo "ERROR: SGLang runtime absent at $LLM_SMALL_RUNTIME" >&2
+        echo "frank-small: build the venv (python3.12 -m venv /home/dank/GitPackages/sglang-cu128" >&2
+        echo "frank-small: and pip install 'sglang[all]' into it) first." >&2
+        return 1
+    fi
+    if [[ ! -f "$LLM_SMALL_MODEL_DIR/model.safetensors.index.json" ]]; then
+        echo "ERROR: payload index absent at $LLM_SMALL_MODEL_DIR" >&2
+        echo "frank-small: run scripts/download-frank-small.sh first;" >&2
         echo "frank-small: refusing to start a unit that cannot load." >&2
         return 1
     fi
+    local count
+    count="$(find "$LLM_SMALL_MODEL_DIR" -maxdepth 1 -name 'model-*-of-*.safetensors' | wc -l)"
+    if [[ "$count" -ne 8 ]]; then
+        echo "ERROR: payload shard count wrong: $LLM_SMALL_MODEL_DIR (found $count, want 8)" >&2
+        return 1
+    fi
     relink_unit frank-small
     run_privileged systemctl daemon-reload
     run_privileged systemctl enable frank-small.service

scripts/download-frank-small.sh

@@ -0,0 +1,93 @@
+#!/usr/bin/env bash
+# Download MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound for frank-small
+# (SGLang, RTX 3090). Public repo — no auth header on the command line.
+#
+# Per-file FRESH downloads, no resume: `curl -C -` once produced a 213 MB
+# oversized file on a 31 GiB payload; a fresh -f fetch plus size+sha256 is
+# the house rule.
+#
+# Usage:
+#   scripts/download-frank-small.sh [DEST_DIR] [--verify-only]
+#
+# LFS shards are verified against the Hub LFS sha256; non-LFS text files
+# against their declared byte size. Idempotent: complete files are skipped.
+set -euo pipefail
+
+REPO="letechlead/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound"
+BASE="https://huggingface.co/${REPO}/resolve/main"
+
+DEST=""
+VERIFY_ONLY=0
+for arg in "$@"; do
+    case "$arg" in
+        --verify-only) VERIFY_ONLY=1 ;;
+        *) DEST="$arg" ;;
+    esac
+done
+DEST="${DEST:-/home/dank/models/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound}"
+
+# name bytes sha256(- = non-LFS, size-only check)
+FILES=(
+  "model-00001-of-00008.safetensors 2946296312 ddb6117c04cb6feaf7c265e5d75efadf21949037d73253a8e4521d40e164366d"
+  "model-00002-of-00008.safetensors 1402134792 2dc78d55d1d33d7b3b21dd6f8b4b817b62c2fb1376e6448b322428798c10e257"
+  "model-00003-of-00008.safetensors 1427365904 5c797d14e345309d67c78306b9de4aa01a21dbd92dd98e40b0ad69b2900e9203"
+  "model-00004-of-00008.safetensors 1420041856 7402f852e2c7a24ebf4694b98a220e71dfb2c93ba3776272cf2acfc65acd8126"
+  "model-00005-of-00008.safetensors 1410655648 991cbf2eda2ff91fc3ffbb15591d7fcac340fb10d9c33bd3da20010e2f3f4090"
+  "model-00006-of-00008.safetensors 1427627856 efc42448054cfb5e3061e154ba4539204088ce95176d689a95b58de885ef7eeb"
+  "model-00007-of-00008.safetensors 2035442408 75a101fc71ae6f2e1f5c4816f711d62cf1d7a0e02ef6e5182361b8c11e72b626"
+  "model-00008-of-00008.safetensors 822153664 0fb90cb50e2d336fbad58bd4c01880eeddbf537c1dca1cf0ae291195d5efbb4b"
+  "tokenizer.json 19989325 06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523"
+  "model.safetensors.index.json 106278 -"
+  "config.json 4608 -"
+  "generation_config.json 161 -"
+  "quantization_config.json 1654 -"
+  "chat_template.jinja 3916 -"
+  "tokenizer_config.json 1168 -"
+  "preprocessor_config.json 443 -"
+  "processor_config.json 1191 -"
+  "README.md 8448 -"
+)
+
+mkdir -p "$DEST"
+status=0
+for entry in "${FILES[@]}"; do
+  read -r name size sha <<<"$entry"
+  f="$DEST/$name"
+  have=0
+  if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]]; then
+    if [[ "$sha" == "-" ]] || sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+      have=1
+    fi
+  fi
+  if (( have )); then
+    echo "OK        $name"
+    continue
+  fi
+  if (( VERIFY_ONLY )); then
+    echo "MISSING   $name"
+    status=1
+    continue
+  fi
+  echo "FETCHING  $name"
+  tmp="$f.part"
+  # no -C resume; -f + --fail-with-body so an HTTP error is not a success
+  curl -fsSL --fail-with-body -o "$tmp" "$BASE/$name"
+  mv "$tmp" "$f"
+  if [[ "$(stat -c%s "$f")" != "$size" ]]; then
+    echo "SIZE FAIL $name ($(stat -c%s "$f") != $size)"
+    status=1
+    continue
+  fi
+  if [[ "$sha" != "-" ]] && ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+    echo "SHA FAIL  $name"
+    status=1
+    continue
+  fi
+  echo "VERIFIED  $name"
+done
+if (( status == 0 )); then
+  echo "DOWNLOAD_DONE $DEST"
+else
+  echo "DOWNLOAD_FAILED $DEST" >&2
+fi
+exit "$status"

scripts/frank-small.env

@@ -1,46 +1,36 @@
-# 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.
+# Tunables for frank-small (letechlead/MiMo-V2.6-Distill-Qwen-9B-INT8-
+# W8A16-AutoRound, qwen3_5 hybrid, in-checkpoint vision) on SGLang,
+# Dankclaw's RTX 3090, since 2026-10-01.
 #
-# 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_FA_ALL_QUANTS=ON
-#   cmake --build build-cuda --target llama-server -j
-# 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).
+# Runtime: SGLang in a python3.12 venv (pip "sglang[all]"):
+#   python3.12 -m venv /home/dank/GitPackages/sglang-cu128
+#   /home/dank/GitPackages/sglang-cu128/bin/pip install "sglang[all]"
+# The venv carries its own CUDA torch + sgl-kernel + flashinfer; it is
+# self-contained and does not touch the host Python (3.14) or the ROCm
+# stack that serves frank-large.
 #
-# 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.
+# Model: MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound — a Qwen3.5-9B
+# distillation at INT8 W8A16 (AutoRound, group 128, symmetric). 8
+# safetensors shards, 12.0 GiB total. The vision tower
+# (qwen3_5_vision, 27 layers) and embed_tokens stay fp16 inside the
+# checkpoint, so the image path needs no separate projector file.
+# Architecture: 32 layers, 8 full-attention (4 KV heads x 256 head_dim)
+# + 24 Gated DeltaNet, native 262144 window. text_config declares
+# mtp_num_hidden_layers = 1, but the shipped safetensors carry NO mtp.*
+# tensors (verified against model.safetensors.index.json 2026-10-01 —
+# base BF16 and this INT8 conversion both omit the head), so there is no
+# spec decode: SGLang would draft with an uninitialised 4.24 GiB ghost
+# model at 0% acceptance and pay the verify tax for nothing.
 #
-# 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.
-#
-# SIZING (RTX 3090, 24576 MiB): CTX_SIZE = PARALLEL x 262144 -- four
-# FULL-window slots, measured to fit: the 4-slot boot idles at 22,346
-# MiB and each extra full-context slot costs 3,450 MiB (measured 1-slot
-# 11,996 -> 4-slot 22,346). A fifth slot projects to ~25.8 GiB, past the
-# card, and the KV pool allocates upfront -- so 4 is the max. Explicit
-# CTX_SIZE bypasses --fit on purpose: --fit maximises the TOTAL pool,
-# which would shrink each slot below the full 262144 window once
-# parallel > 1.
-#
-# Vision + audio: --mmproj loads the BF16 projector (11 tensors, 52M
-# params; it carries an audio encoder too). The fleet's image path lives
-# here, which is why halogen no longer sets HALOGEN_VISION_TOWER. Audio
-# WORKS: input_audio content parts transcribe verbatim (verified
-# 2026-09-17 with a 16k mono WAV).
+# SIZING (RTX 3090), measured 2026-10-01: the 0.98 budget holds the
+# checkpoint (11,354 MiB) + the DeltaNet ssm state pool (795 MiB at 32
+# bf16 slots) + the KV pool. The engine's autofit picks a 687,388-token
+# pool and leaves ~0.53 GB — too little: Triton's deferred kernel loads
+# take most of it after boot, and eager-prefill activations then OOM on
+# the first long request. The pool is therefore PINNED at 606,208 tokens
+# (4 x 151,552), which leaves ~0.8 GB for the prefill workspace; a 170k
+# single request and 4 concurrent 54k requests are verified against it.
+# The ssm pool is the 4.5 GiB the weights-only arithmetic misses.
 #
 # Sampling: greedy by default (the fleet contract); a client that sends a
 # temperature gets its own, and the harness applies per-model overrides
@@ -50,69 +40,41 @@
 # 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,
-# FA_ALL_QUANTS=ON.
-LLAMA_BIN=/home/dank/GitPackages/llama.cpp-mainline/build-cuda/bin/llama-server
+# SGLang runtime: python3.12 venv, self-contained CUDA stack.
+SGLANG_BIN=/home/dank/GitPackages/sglang-cu128/bin/sglang
 
-# 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
+# Model package (8 shards + configs, sha256-verified by
+# scripts/download-frank-small.sh).
+MODEL_DIR=/home/dank/models/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound
 
 # 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.
+# 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
 
-# Four FULL 262144-token contexts, one per slot (CTX_SIZE is the total
-# pool; --parallel divides it). See the SIZING note above for the fit
-# arithmetic; a fifth slot does not fit.
-CTX_SIZE=1048576
-PARALLEL=4
-CACHE_TYPE_K=q8_0
-CACHE_TYPE_V=q8_0
-# CPU RAM cache cap in MiB (build default 8192). This host is memory-tight
-# (frank-large's 70 GiB GTT plus the rest of the stack), and Gemma4 runs
-# fully on the 3090 (-ngl 999), so the CPU-side cache is not the hot path;
-# cap it at 2048 to give back ~6 GiB of LPDDR. Gemma4 is not a DeltaNet
-# model, so the >12.8 GiB CACHE_RAM floor does not apply.
-CACHE_RAM=2048
+# Four slots on fp8 KV. The pool is pinned (see SIZING above): 606,208
+# tokens = 4 x 151,552, so the slot window is 151,552. A single request
+# may still grow to the whole pool (a 170k prompt is verified); the grid
+# is the four-way concurrency contract.
+MEM_FRACTION=0.98
+MAX_TOTAL_TOKENS=606208
+CONTEXT_LENGTH=151552
+MAX_RUNNING=4
+KV_DTYPE=fp8_e4m3
+QUANTIZATION=auto-round
+# DeltaNet (mamba) recurrent states: the ssm state pool is the single
+# biggest hidden consumer on this card. The engine autofills the slot
+# COUNT to spend a fixed ~5.1 GB budget regardless of dtype (fp32 at 110
+# slots, bf16 at 217 — same 5.1 GB), so BOTH dials are pinned below:
+# bf16 dtype + 32 slots = 795 MiB.
+MAMBA_SSM_DTYPE=bfloat16
+# 32 slots is 8x the 4-way concurrency: enough for the radix mamba cache
+# to keep shared-prefix states, small enough to leave the KV pool room.
+MAX_MAMBA_CACHE_SIZE=32
 
-# Batch geometry: 8192 logical / 1024 physical. Measured on this card at
-# max length (254k-token prefill / 253k-ctx decode, 4 slots, q8 KV):
-# ubatch 512 -> pp 915 t/s, tg@250k 90-204; ubatch 1024 -> pp 962,
-# tg 257-302. Larger ubatches (2048) OOM the MTP draft context's pp
-# compute buffer (~3.3 GiB against 2.2 GiB headroom) and must not be
-# tried. Idle VRAM is 23,300 MiB at this geometry.
-BATCH_SIZE=8192
-UBATCH_SIZE=1024
-
-# 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.
-NUM_THREADS=8
-THREAD_BATCH=8
-
-# Every layer on the 3090, with flash attention (required for q8 KV).
-NGL=999
-FLASH_ATTN=on
-
-# Speculative decoding: the MTP sidecar (draft context) chained with the
-# draftless ngram-mod matcher. Draft depth and busy-wait level are made
-# explicit here (both were the implicit build defaults: 3 and 50).
-# Measured at 250k ctx: depth 4 + poll 100 DECODED WORSE (230-257 t/s)
-# than depth 3 + poll 50 (257-302 t/s) — the longer verification round
-# costs more attention re-read at long context than the extra accepted
-# token earns. Keep 3/50.
-SPEC_TYPE=draft-mtp,ngram-mod
-SPEC_DRAFT_N_MAX=3
-POLL_LEVEL=50
-
-# Greedy default (fleet contract); reasoning is extracted into
-# reasoning_content with an unlimited budget (the model decides).
-TEMPERATURE=0.0
-REASONING_FORMAT=deepseek
-REASONING_BUDGET=-1
+# Reasoning is extracted into reasoning_content; tools use the qwen3_coder
+# grammar (both parsers per the SGLang Qwen3.5 cookbook).
+REASONING_PARSER=qwen3
+TOOLCALL_PARSER=qwen3_coder

scripts/frank-small.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=llama.cpp Qwen3.8-27B GSQ-RCO IQ3_S MTP+vision (dankclaw, frank-small)
+Description=SGLang MiMo-V2.6-Distill-Qwen-9B-INT8 (qwen3_5 hybrid, MTP+vision) 4x172k fp8 KV (dankclaw, frank-small)
 After=network-online.target
 Wants=network-online.target
 
@@ -8,8 +8,7 @@ Type=simple
 User=dank
 Group=dank
 # CUDA pins its staging buffers, so the process needs the memlock budget even
-# though the weights themselves are copied into VRAM. Parity with the halogen
-# quadlet's Ulimit=memlock=-1:-1 and the retired ik unit.
+# though the weights themselves are copied into VRAM.
 LimitMEMLOCK=infinity
 Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env"
 ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh

scripts/serve-frank-small.sh

@@ -1,37 +1,28 @@
 #!/usr/bin/env bash
-# Serve HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced (Q4_K_M) as
-# frank-small on Dankclaw's RTX 3090 via mainline llama.cpp.
+# Serve letechlead/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound as
+# frank-small on Dankclaw's RTX 3090 via SGLang.
 #
-# Topology: the whole model lives in VRAM (-ngl 999) -- 6.87 GiB of Q4_K_M
-# weights plus the BF16 vision projector and q8_0 KV inside the card's
-# 24 GiB. The host CPU only tokenizes and samples here; this box's CPU
-# belongs to the halogen engine that serves frank-large.
+# Topology: the whole checkpoint (12.0 GiB, INT8 W8A16 AutoRound) lives in
+# VRAM; the 3090's 24 GiB holds weights + a ~11.8 GiB fp8 KV pool at
+# --mem-fraction-static 0.98. The host CPU only tokenizes.
 #
-# MTP: this model's Multi-Token Prediction head ships as a SEPARATE file
-# (mtp-gemma-4-12B-it.gguf, arch gemma4-assistant, 4 nextn layers). It is
-# passed via --model-draft with --spec-type draft-mtp: 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 this chain is the
-# only shape that carries both.
+# Architecture: qwen3_5 hybrid — 32 layers, 8 full-attention + 24 Gated
+# DeltaNet, native 262144 window, and a vision tower (qwen3_5_vision)
+# baked into the safetensors: no separate projector file, the image path
+# is in the checkpoint. The config declares an MTP layer, but the shipped
+# weights carry none (no mtp.* tensors in the index), so this service runs
+# WITHOUT speculative decoding — a NEXTN draft would be an uninitialised
+# 4.24 GiB ghost model drafting at 0% acceptance.
 #
-# Context: CTX_SIZE is set explicitly to PARALLEL x 262144 so every slot
-# gets the model's FULL window; --fit (the CTX_SIZE-unset branch below)
-# maximises the TOTAL pool instead, which would divide a smaller window
-# across slots. The 4-slot layout is measured to fit the card (see the
-# SIZING note in frank-small.env); more slots would fail the KV allocation.
+# Context: CONTEXT_LENGTH x MAX_RUNNING=4 slots must fit the fp8 KV pool,
+# which the engine autofits around the weights AND the DeltaNet ssm state
+# pool (see frank-small.env). The mamba pool defaults to ~5.1 GB, so it is
+# pinned (bf16, 32 slots). With the grid at its measured fit the card has
+# no headroom for prefill CUDA-graph capture, so prefill runs eager
+# (--disable-prefill-cuda-graph); decode graphs are untouched.
 #
-# Vision + audio: --mmproj loads the BF16 projector, which also carries
-# an audio encoder — input_audio content parts transcribe verbatim
-# (verified 2026-09-17). The fleet's image path lives here, which is why
-# halogen no longer sets HALOGEN_VISION_TOWER.
-#
-# Sampling: greedy by default (the fleet contract). Clients that send their own
-# temperature get their own values, and the harness overrides per model from
-# models.yml. --jinja is pinned even though this build defaults it on: the
-# model's own template supplies reasoning_effort, preserve_thinking and the
-# tool-call grammar, and a future build that flips that default must not
-# silently take tools away.
+# Sampling: greedy by default (the fleet contract); clients that send their
+# own temperature get their own values.
 #
 # Tunables come from frank-small.env unless FRANK_SMALL_ENV_FILE overrides it.
 set -euo pipefail
@@ -46,101 +37,61 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/GitPackages/llama.cpp-mainline/build-cuda/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/Gemma4-12B-QAT}"
-: "${MODEL_FILE:=Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf}"
-: "${MMPROJ_PATH:=$MODEL_DIR/mmproj-Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf}"
-# NOTE: the fallback above was the retired ISTA-DASLab Qwen3.8-27B GSQ-RCO
-# payload, which frank-small served on 2026-09-16/17 and which no longer
-# exists on disk. frank-small.env has always overridden it, so the drift was
-# invisible — but a missing or unreadable env file would have left this
-# script pointing at a payload that is not there, turning a config problem
-# into a "missing asset" that names the wrong model.
-: "${DRAFT_FILE:=}"
+: "${SGLANG_BIN:=/home/dank/GitPackages/sglang-cu128/bin/sglang}"
+: "${MODEL_DIR:=/home/dank/models/MiMo-V2.6-Distill-Qwen-9B-INT8-W8A16-AutoRound}"
 : "${ALIAS:=frank-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
-: "${CTX_SIZE:=}"
-: "${PARALLEL:=1}"
-: "${CACHE_TYPE_K:=f16}"
-: "${CACHE_TYPE_V:=f16}"
-: "${CACHE_RAM:=8192}"
-: "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=512}"
-# Decode-shape knobs: the MTP drafter's per-round proposal length (build
-# default 3; the Gemma4 sidecar carries 4 nextn layers) and the engine's
-# busy-wait level (build default 50).
-: "${SPEC_DRAFT_N_MAX:=3}"
-: "${POLL_LEVEL:=50}"
-: "${NUM_THREADS:=8}"
-: "${THREAD_BATCH:=8}"
-: "${NGL:=999}"
-: "${FLASH_ATTN:=on}"
-: "${SPEC_TYPE:=draft-mtp}"
-: "${TEMPERATURE:=0.0}"
-: "${REASONING_FORMAT:=deepseek}"
-: "${REASONING_BUDGET:=-1}"
+: "${MEM_FRACTION:=0.98}"
+: "${CONTEXT_LENGTH:=151552}"
+: "${MAX_TOTAL_TOKENS:=606208}"
+: "${MAX_RUNNING:=4}"
+: "${KV_DTYPE:=fp8_e4m3}"
+: "${QUANTIZATION:=auto-round}"
+: "${REASONING_PARSER:=qwen3}"
+: "${TOOLCALL_PARSER:=qwen3_coder}"
+: "${MAMBA_SSM_DTYPE:=bfloat16}"
+: "${MAX_MAMBA_CACHE_SIZE:=32}"
 
 # Fail loudly rather than half-loading a model into VRAM: a missing file here
 # is a download that has not finished, and the unit's restart policy would
 # otherwise turn that into a crash loop that reads like a runtime fault.
-for path in "$LLAMA_BIN" "$MODEL_DIR/$MODEL_FILE" "$MMPROJ_PATH"; do
+for path in "$SGLANG_BIN" "$MODEL_DIR/model.safetensors.index.json" \
+    "$(cd -- "$(dirname -- "$SGLANG_BIN")/.." && pwd)/cuda-nvcc/usr/local/cuda-13.0/bin/nvcc"; do
     [[ -e "$path" ]] || { echo "frank-small: missing $path" >&2; exit 1; }
 done
-if [[ -n "${DRAFT_FILE:-}" ]]; then
-    [[ -e "$MODEL_DIR/$DRAFT_FILE" ]] || { echo "frank-small: missing $MODEL_DIR/$DRAFT_FILE" >&2; exit 1; }
+shard_count=$(find "$MODEL_DIR" -maxdepth 1 -name 'model-*.safetensors' | wc -l)
+if [[ "$shard_count" -ne 8 ]]; then
+    echo "frank-small: expected 8 safetensors shards in $MODEL_DIR, found $shard_count" >&2
+    exit 1
 fi
 
 # The UVM device node is created lazily by nvidia-modprobe on the first CUDA
 # open after boot; make sure it exists before the server needs it.
 nvidia-modprobe -u -c=0 2>/dev/null || true
 
-MMPROJ_ARGS=()
-if [[ -n "${MMPROJ_PATH:-}" && -f "$MMPROJ_PATH" ]]; then
-    MMPROJ_ARGS=(--mmproj "$MMPROJ_PATH")
-fi
+# FlashInfer JITs its attention kernels with nvcc at boot. The host's
+# /usr/bin/nvcc is CUDA 12.4 and dies on `--compress-mode` (a 12.8+
+# option), so the venv carries a matching CUDA 13.0 nvcc (extracted from
+# the cuda-nvcc-13-0 deb); it must shadow the system one on PATH.
+export PATH="$(cd -- "$(dirname -- "$SGLANG_BIN")/.." && pwd)/cuda-nvcc/usr/local/cuda-13.0/bin:$PATH"
 
-SPEC_ARGS=()
-if [[ -n "${SPEC_TYPE:-}" && "$SPEC_TYPE" != "none" ]]; then
-    SPEC_ARGS=(--spec-type "$SPEC_TYPE" --spec-draft-n-max "$SPEC_DRAFT_N_MAX")
-fi
-
-DRAFT_ARGS=()
-if [[ -n "${DRAFT_FILE:-}" ]]; then
-    DRAFT_ARGS=(--model-draft "$MODEL_DIR/$DRAFT_FILE")
-fi
-
-# CTX_SIZE set -> pinned context. Unset -> --fit sizes the KV pool against
-# whatever the weights, projector, draft context and compute buffers leave
-# on the card; the engine prints the chosen value at startup.
-if [[ -n "${CTX_SIZE:-}" ]]; then
-    CTX_ARGS=(--ctx-size "$CTX_SIZE")
-else
-    CTX_ARGS=(--fit on)
-fi
-
-exec "$LLAMA_BIN" \
-    --model "$MODEL_DIR/$MODEL_FILE" \
-    "${MMPROJ_ARGS[@]}" \
-    "${DRAFT_ARGS[@]}" \
-    --alias "$ALIAS" \
+# Sampling: SGLang has no server-wide sampling defaults; the harness sends
+# its per-model recipe from models.yml (compat.extraBody), and other clients
+# get the engine's own defaults.
+exec "$SGLANG_BIN" serve \
+    --model-path "$MODEL_DIR" \
+    --served-model-name "$ALIAS" \
     --host "$BIND_ADDR" \
     --port "$LISTEN_PORT" \
-    --gpu-layers "$NGL" \
-    --flash-attn "$FLASH_ATTN" \
-    "${CTX_ARGS[@]}" \
-    --parallel "$PARALLEL" \
-    --batch-size "$BATCH_SIZE" \
-    --ubatch-size "$UBATCH_SIZE" \
-    --threads "$NUM_THREADS" \
-    --threads-batch "$THREAD_BATCH" \
-    --poll "$POLL_LEVEL" \
-    --cache-type-k "$CACHE_TYPE_K" \
-    --cache-type-v "$CACHE_TYPE_V" \
-    --cache-ram "$CACHE_RAM" \
-    "${SPEC_ARGS[@]}" \
-    --jinja \
-    --metrics \
-    --temp "$TEMPERATURE" \
-    --reasoning-format "$REASONING_FORMAT" \
-    --reasoning-budget "$REASONING_BUDGET"
+    --mem-fraction-static "$MEM_FRACTION" \
+    --context-length "$CONTEXT_LENGTH" \
+    --max-running-requests "$MAX_RUNNING" \
+    --kv-cache-dtype "$KV_DTYPE" \
+    --quantization "$QUANTIZATION" \
+    --reasoning-parser "$REASONING_PARSER" \
+    --tool-call-parser "$TOOLCALL_PARSER" \
+    --mamba-ssm-dtype "$MAMBA_SSM_DTYPE" \
+    --max-mamba-cache-size "$MAX_MAMBA_CACHE_SIZE" \
+    --disable-prefill-cuda-graph \
+    --max-total-tokens "$MAX_TOTAL_TOKENS"