frank-default-large: swap to kingjones STRIX model on card-pinned kingjones30/ROCmFPX runtime

- runtime: charlie build-qwen38 -> kingjones30/ROCmFPX (card recipe
  build, LLAMA_BUILD_WEBUI=OFF since npm/HF-bucket provisioning fails;
  all 35 of our serving flags verified present in the tree)
- model: agentionai FAST imatrix -> kingjones777 STRIX single GGUF
  (on-host copy sha256 == HF LFS oid c6770d74...49fa verified)
- args unchanged from our validated profile (401408x2, b4096/ub512,
  t16/tb16, f16 KV, fa on, fit off); mmap stays default per card
  (PLE streams via page cache; --no-mmap = silent cgroup OOM)

scripts/frank-default-large.env

@@ -1,49 +1,51 @@
-# Tunables for frank-default-large (agentionai/Qwen3.8-Flash-Next-ROCmFP4-
-# FAST-imatrix-GGUF on the charlie12345/ROCmFPX llama.cpp runtime,
-# build-qwen38, Dankclaw, Strix Halo gfx1151 unified memory).
+# Tunables for frank-default-large (kingjones777/Qwen3.8-Flash-Next-ROCmFP4-
+# STRIX-GGUF on the kingjones30/ROCmFPX llama.cpp runtime, Dankclaw,
+# Strix Halo gfx1151, unified memory).
 #
-# Runtime: charlie12345/ROCmFPX llama.cpp at
-# /home/dank/GitPackages/ROCmFPX/build-qwen38 (HIP, ROCm 7.2.4, gfx1151,
-# PR #27742 qwen4exp merged). The ROCmFP4 quant types are hand-ported from
-# ciru-ai/ROCmFPX; upstream llama.cpp cannot load this GGUF. Replaced the
-# jcbtc CIRU v1.1 (ciru-ai runtime) and kingjones STRIX_LEAN deployments.
+# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
+# qwen4exp-on-rocmfpx-d3ca537 patch applied — the model card's pinned
+# runtime: ROCmFP4 tensor types AND the qwen4exp architecture in one
+# tree; stock llama.cpp and charlie's fork alone cannot load this GGUF).
+# Built per the card recipe:
+#   cmake -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release
+# at /home/dank/GitPackages/kingjones-ROCmFPX/build.
+# Replaced the agentionai ROCmFP4-FAST imatrix deployment (charlie's
+# build-qwen38 runtime) on 2026-08-30.
 #
 # Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
 # 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
-# 1. Flash attention is ON. fa on used to abort graph build: the QSA
-#    indexer path called ggml_fill on the F16-cast kq mask (ggml_fill
-#    asserts GGML_TYPE_F32 at ggml.c:5371). Fixed in the fork source by
-#    the QSA F32-mask patch (scripts/patches/qwen4exp-qsa-f32-mask.patch,
-#    sha256 f2f4a486e21cfad80bfa42683281d18e1cba22fa43c5e0e2aa0cfdbe141e925f)
-#    and the rebuilt binary at LLAMA_BIN already carries the fix. A clean
-#    rebuild must re-apply: git apply scripts/patches/qwen4exp-qsa-f32-mask.patch
-#    inside /home/dank/GitPackages/ROCmFPX before make. Verified live:
-#    --flash-attn on + v2 main at CTX_SIZE=32768 loads, health 200, real
-#    completion.
-# 2. The MTP draft head does NOT load on this binary. The qwen4exp loader
-#    requires blk.0.hc_attn_norm.weight per layer; the agentionai FAST
-#    head carries only blk.48 (verified 3x: EasiiX Q8_0 + FAST against
-#    kingjones STRIX_LEAN, FAST against this v2 main). Speculative
-#    decoding therefore runs ngram-mod only. The 2.28 GiB head stays on
-#    disk in case a compatible binary/head pair appears.
+# at layer 1), Q4_0_ROCMFP4_STRIX (file_type 105), 113.47 GiB single
+# file. STRIX is the top quality tier: PLE table at Q8_0 (50.66 GiB),
+# token embeddings + lm head at Q6_K. The PLE table NEVER enters GPU
+# memory — it streams from the file through the OS page cache. Two hard
+# card constraints:
+#  1. mmap MUST stay enabled (default) — --no-mmap forces the 50.66 GiB
+#     table into anonymous memory and the cgroup killer takes the
+#     process with nothing in the server log (only dmesg).
+#  2. Do NOT pin the PLE tensor to CPU with -ot — measured gen fell
+#     ~23 -> 13.4 tok/s; the kernel streams it better.
+# NOTE: the card's own build_attn_qsa still calls ggml_fill on the
+# F16-cast kq mask (the path that aborted our charlie build with
+# --flash-attn on before scripts/patches/qwen4exp-qsa-f32-mask.patch).
+# If a clean kingjones-tree build aborts graph build with
+# GGML_ASSERT(a-type == GGML_TYPE_F32), port that fix (F32 base mask +
+# cast at the attention call) into this tree and rebuild.
 #
 # WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The ROCm HIP runtime reads those bare env vars (see the 2026-08-13 TEMP
 # incident). llama.cpp reads --host/--port/--temp as CLI flags, never as
 # env vars.
 
-# ROCmFPX (build-qwen38) runtime binary.
-LLAMA_BIN=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server
+# kingjones30/ROCmFPX runtime binary (card recipe build).
+LLAMA_BIN=/home/dank/GitPackages/kingjones-ROCmFPX/build/bin/llama-server
 
 # Model package from
-# https://huggingface.co/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF
-# Layout: v2/ joined-layout GGUF (PLE n-gram table as a single
-# per_layer_token_embd.weight tensor — the layout the charlie12345/ROCmFPX
-# qwen4exp loader requires; the root -ple16 file splits the table per head
-# and only loads in the LaurentZuijdwijk Vulkan fork). mmproj/ vision tower.
-# The MTP draft head lives in /home/dank/models/mtp-Qwen3.8-Flash-Next-FAST
-# (already on the host).
-MODEL_DIR=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/v2
-MODEL_FILE=Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-v2.gguf
+# https://huggingface.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF
+# Layout: single unsharded GGUF, text-only (the repo ships no mmproj;
+# the vision tower below is borrowed from the agentionai FAST package —
+# same base model, f16 — kept only if it loads clean, drop
+# MMPROJ_PATH if it does not).
+MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX
+MODEL_FILE=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf
 MMPROJ_PATH=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf
 
 # Qwen-Sharp chat template (tracked in the repo, staged on the host). The
@@ -62,11 +64,14 @@ LISTEN_PORT=7770
 # ubatch 512, 16+16 threads, f16 KV, 16 context checkpoints, 8 GiB
 # prompt cache. --fit off: auto-fit segfaults on this model's
 # hyper-connection/indexer config; -ngl 999 puts every layer on the
-# SVM-backed GPU pool.
+# SVM-backed GPU pool. ubatch 512 matches the card's re-measurement
+# (-ub 1024/2048/4096 showed no effect; -t 32 vs 16 is noise).
 #
-# CTX_SIZE=401408 / PARALLEL=2: untested experiment. At 32768×1 the
-# context buffer was ~13 GiB and total ~100 GiB in the 119.3 GiB HIP
-# heap. Doubling slots × 12× context could OOM — verify load.
+# CTX_SIZE=401408 / PARALLEL=2: carried over from the FAST deployment
+# where it loaded clean (~74 s, health 200). The card measures the full
+# 262144 window at ~71.7 GiB GTT at load on the same 128 GB board; QSA
+# caps KV growth so the extra window is cheap. KV footprint scales
+# with the 12 attention layers only. Verify load on first STRIX boot.
 CTX_SIZE=401408
 PARALLEL=2
 
@@ -104,7 +109,11 @@ HSA_OVERRIDE_GFX_VERSION=11.5.1
 VERBOSITY=4
 
 
-# Speculative decoding: disabled.
+# Speculative decoding: disabled. The card's Usage block ships no spec
+# flags. The Flash-Next MTP heads do not load on this loader (requires
+# per-layer blk.N.hc_attn_norm; every head carries only blk.48 —
+# verified 3x on build-qwen38). DRAFT_MODEL_* point at the retired
+# agentionai FAST head and are unused while SPEC_TYPE=none.
 DRAFT_MODEL_DIR=/home/dank/models/mtp-Qwen3.8-Flash-Next-FAST
 DRAFT_MODEL_FILE=Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST.gguf
 SPEC_TYPE=none

scripts/serve-frank-large.sh

@@ -1,29 +1,31 @@
 #!/usr/bin/env bash
-# Serve agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF as
-# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
-# (build-qwen38, PR #27742 qwen4exp merged) on Dankclaw (Strix Halo
-# gfx1151, unified memory).
+# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF as
+# frank-default-large via the kingjones30/ROCmFPX llama.cpp runtime on
+# Dankclaw (Strix Halo gfx1151, unified memory).
 #
-# Runtime: charlie12345/ROCmFPX llama.cpp built at
-# /home/dank/GitPackages/ROCmFPX/build-qwen38 (HIP, gfx1151, ROCm 7.2.4).
-# The ROCmFP4 quant types (Q4_0_ROCMFP4_FAST) are hand-ported from
-# ciru-ai/ROCmFPX; upstream llama.cpp cannot load this GGUF.
+# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
+# model card's qwen4exp-on-rocmfpx patch) built at
+# /home/dank/GitPackages/kingjones-ROCmFPX/build (HIP, gfx1151,
+# ROCm 7.2.4, card recipe). The ROCmFP4 quant types plus the qwen4exp
+# architecture must be in one tree; stock llama.cpp cannot load this
+# GGUF.
 #
 # Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
 # 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
-# at layer 1) quantized Q4_0_ROCMFP4_FAST, imatrix-calibrated, 87.06 GiB.
-# The n-gram PLE table is a single per_layer_token_embd.weight tensor —
-# fully VRAM-resident, no sidecar, no --ngram-on-disk.
+# at layer 1) quantized Q4_0_ROCMFP4_STRIX, 113.47 GiB single file. The
+# 50.66 GiB PLE n-gram table stays OUT of GPU memory and streams via
+# mmap from the OS page cache — never add --no-mmap or -ot for it.
 #
 # Profile: card sampling table (temp 0.7, top_p 0.80, top_k 20, min_p 0.0,
-# presence 1.5 — non-thinking instruct) mixed with the validated
-# build-qwen38 serving profile: ctx 262144 x 1 slot, b 4096 / ub 4096,
-# t 16 / tb 16, f16 KV, fa OFF (see KNOWN CONSTRAINTS in the env file:
-# flash-attn on aborts graph build on the QSA indexer path), cont-batching,
-# prompt cache + 8 GiB cache-ram + idle-slot cache, 16 ctx checkpoints,
-# --fit off (auto-fit segfaults on qwen4exp hyper-connection config).
-# Speculative decoding is ngram-mod only; the MTP head does not load on
-# build-qwen38 (loader requires blk.0.hc_attn_norm.weight it lacks).
+# presence 1.5 — non-thinking instruct) mixed with the validated serving
+# profile: ctx 401408 x 2 slots, b 4096 / ub 512, t 16 / tb 16, f16 KV,
+# fa on (if the graph build aborts on the QSA F16 mask, see the note in
+# the env file: port scripts/patches/qwen4exp-qsa-f32-mask.patch into
+# this tree and rebuild), cont-batching, prompt cache + 8 GiB cache-ram
+# + idle-slot cache, 16 ctx checkpoints, --fit off (auto-fit segfaults
+# on qwen4exp hyper-connection config). Speculative decoding off: the
+# Flash-Next MTP heads do not load on this loader; the card ships no
+# spec flags.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -36,10 +38,10 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/v2}"
-: "${MODEL_FILE:=Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-v2.gguf}"
-: "${MMPROJ_PATH:=$MODEL_DIR/../mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
+: "${LLAMA_BIN:=/home/dank/GitPackages/kingjones-ROCmFPX/build/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX}"
+: "${MODEL_FILE:=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf}"
+: "${MMPROJ_PATH:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
 : "${CHAT_TEMPLATE_KWARGS:={}}"
 : "${ALIAS:=frank-default-large}"
@@ -122,8 +124,8 @@ if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
     fi
 fi
 
-# The agentionai FAST package includes the model's own vision tower (f16,
-# lossless). Pass --mmproj only when MMPROJ_PATH points at a readable file.
+# The STRIX repo ships no mmproj; this is the agentionai FAST package's
+# f16 vision tower for the same base model. Passed only when readable.
 MMPROJ_ARGS=()
 if [[ -n "${MMPROJ_PATH:-}" && -r "${MMPROJ_PATH:-}" ]]; then
     MMPROJ_ARGS=(--mmproj "$MMPROJ_PATH")