Swap fleet naming + restore Qwen3.6-35B-A3B Q6_K_P on Dankserver

- Restore the pre-2026-08-17 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Q6_K_P + ngram-mod setup as frank-default-small on Dankserver (port 7770, upstream llama.cpp b10121, MoE experts on CPU via --n-cpu-moe 36). - Rename the CIRU Qwen3.8-27B ActiveFPX setup from frank-default-small to frank-default-large (Dankclaw, port 52625); bump to CTX_SIZE=262144 (native max) and PARALLEL=2 (96 GiB unified pool). - Retire the Qwen3.8-27B IQ4_XS FastMTP frank-default-large (Dankserver) to .AGENTTRASH. - deploy.sh: SERVICE[dankserver]=frank-default-small, SERVICE[dankclaw]=frank-default-large; HEALTH_WAIT[dankserver]=600.
2026-08-18 00:32:26 -07:00
1 parent fe1d834d37
commit 1ba9618fcc
@@ -1,14 +1,16 @@
 #!/usr/bin/env bash
-# Serve the Qwen3.8-27B HauhauCS Aggressive IQ4_XS on Dankserver (RTX 3090).
+# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge as frank-default-large
+# via the CIRU ROCmFPX llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
 #
-# Runs a patched llama-server (HauhauCS FastMTP build, commit 4df29be +
-# HauhauCS-FastMTP-llama.cpp.patch) with the FastMTP draft sidecar and the
-# ngram-mod fallback. There is no pipeline split: the whole model lives on
-# the 3090.
+# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
+# qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) against the private
+# TheRock ROCm 7.15 SDK (kept in the retired ling3-ciru venv). The model is
+# a GGUF with optional PromptForge companion views (FFN/GDN .pfs) that enable
+# CIRU DualView prompt acceleration. Native depth-4 MTP speculative decoding.
 #
-# The FastMTP draft sidecar requires the patched executable. Loading the
-# draft with the stock binary fails with "expected 5120, 248320, got 5120,
-# 32768" (see the HauhauCS repo README).
+# The model card requires ROCm 7.15 (not the system ROCm 7.2.4) for the
+# advertised Strix Halo performance. LD_LIBRARY_PATH therefore points at the
+# 7.15 SDK libraries first. An older system ROCm must not precede them.
 #
 # Tunables come from frank-default-large.env in this directory unless
 # FRANK_LARGE_ENV_FILE overrides that path.
@@ -24,44 +26,52 @@ if [[ -f "$ENV_FILE" ]]; then
 fi

 # --- defaults (used when the env file does not set them) -------------------
-: "${MODEL_DIR:=/home/dank/models/hauhaucs-qwen38}"
-: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf}"
-: "${DRAFT_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-FastMTP-32K.gguf}"
-: "${LLAMA_BIN:=/home/dank/llama.cpp-fastmtp/build/bin/llama-server}"
+: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/CIRU-Qwen3.8-27B-ActiveFPX}"
+: "${MODEL_FILE:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-v2.gguf}"
+: "${FFN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-FFN.pfs}"
+: "${GDN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-GDN.pfs}"
+: "${ROCM_DEVEL:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel}"
+: "${ROCM_LIB:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries}"
+: "${ROCM_CORE:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core}"
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
-: "${LISTEN_PORT:=7770}"
-: "${CTX_SIZE:=131072}"
-: "${PARALLEL:=1}"
-: "${SPEC_DEFAULT:=1}"
-: "${MTP:=1}"
-: "${SPEC_DRAFT_N_MAX:=2}"
-: "${SPEC_DRAFT_NGL:=all}"
-: "${SPEC_DRAFT_P_MIN:=0}"
-: "${SPEC_NGRAM_MOD_N_MIN:=48}"
-: "${SPEC_NGRAM_MOD_N_MAX:=64}"
-: "${SPEC_NGRAM_MOD_N_MATCH:=24}"
-: "${CACHE_TYPE_K:=q8_0}"
-: "${CACHE_TYPE_V:=f16}"
+: "${LISTEN_PORT:=52625}"
+: "${CTX_SIZE:=262144}"
+: "${PARALLEL:=2}"
 : "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=1024}"
-: "${TEMPERATURE:=1.0}"
-: "${TOP_K:=20}"
+: "${UBATCH_SIZE:=2048}"
+: "${CACHE_TYPE_K:=f16}"
+: "${CACHE_TYPE_V:=f16}"
+: "${CTX_CHECKPOINTS:=32}"
+: "${CACHE_RAM:=8192}"
+: "${SPEC_DRAFT_N_MAX:=4}"
+: "${SPEC_DRAFT_N_MIN:=0}"
+: "${SPEC_DRAFT_P_MIN:=0.0}"
+: "${SPEC_DRAFT_P_SPLIT:=0.10}"
+: "${TEMPERATURE:=0.7}"
 : "${TOP_P:=0.95}"
-: "${MIN_P:=0.0}"
-: "${THREADS:=8}"
-: "${THREADS_HTTP:=1}"
+: "${REASONING:=on}"
+: "${REASONING_FORMAT:=deepseek}"
 : "${VERBOSITY:=4}"

 MODEL="$MODEL_DIR/$MODEL_FILE"
-DRAFT="$MODEL_DIR/$DRAFT_FILE"
+export PROMPTFORGE_SIDECAR="$MODEL_DIR/$FFN_PFS"
+export PROMPTFORGE_GDN_SIDECAR="$MODEL_DIR/$GDN_PFS"
+export PROMPTFORGE_MODE="m2048_fused_tail1476"
+export GGML_CUDA_GRAPH_OPT=0
+export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1

 if [[ ! -f "$MODEL" ]]; then
    echo "missing required file: $MODEL" >&2
    exit 1
 fi
-if [[ ! -f "$DRAFT" ]]; then
-    echo "missing draft file: $DRAFT" >&2
+if [[ ! -f "$PROMPTFORGE_SIDECAR" ]]; then
+    echo "missing PromptForge FFN companion: $PROMPTFORGE_SIDECAR" >&2
+    exit 1
+fi
+if [[ ! -f "$PROMPTFORGE_GDN_SIDECAR" ]]; then
+    echo "missing PromptForge GDN companion: $PROMPTFORGE_GDN_SIDECAR" >&2
    exit 1
 fi
 if [[ ! -x "$LLAMA_BIN" ]]; then
@@ -69,40 +79,41 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
    exit 1
 fi

-# --- speculative decoding: FastMTP (MTP) first, then ngram-mod fallback ----
-SPEC_ARGS=()
-SPEC_ARGS+=(--spec-type draft-mtp)
-SPEC_ARGS+=(--spec-draft-model "$DRAFT")
-SPEC_ARGS+=(--spec-draft-n-max "$SPEC_DRAFT_N_MAX")
-SPEC_ARGS+=(--spec-draft-ngl "$SPEC_DRAFT_NGL")
-SPEC_ARGS+=(--spec-draft-p-min "$SPEC_DRAFT_P_MIN")
-if [[ "$SPEC_DEFAULT" == "1" ]]; then
-    SPEC_ARGS+=(--spec-default)
-    SPEC_ARGS+=(--spec-ngram-mod-n-min "$SPEC_NGRAM_MOD_N_MIN")
-    SPEC_ARGS+=(--spec-ngram-mod-n-max "$SPEC_NGRAM_MOD_N_MAX")
-    SPEC_ARGS+=(--spec-ngram-mod-n-match "$SPEC_NGRAM_MOD_N_MATCH")
-fi
+# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
+export ROCM_PATH="$ROCM_DEVEL"
+export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"

 exec "$LLAMA_BIN" \
    --model "$MODEL" \
-    "${SPEC_ARGS[@]}" \
-    --gpu-layers all \
-    --no-mmap \
-    --flash-attn on \
-    --ctx-size "$CTX_SIZE" \
-    --parallel "$PARALLEL" \
-    --cache-type-k "$CACHE_TYPE_K" \
-    --cache-type-v "$CACHE_TYPE_V" \
-    --batch-size "$BATCH_SIZE" \
-    --ubatch-size "$UBATCH_SIZE" \
-    --temp "$TEMPERATURE" \
-    --top-k "$TOP_K" \
-    --top-p "$TOP_P" \
-    --min-p "$MIN_P" \
-    --threads "$THREADS" \
-    --threads-http "$THREADS_HTTP" \
-    --jinja \
    --alias "$ALIAS" \
-    -lv "$VERBOSITY" \
    --host "$BIND_ADDR" \
-    --port "$LISTEN_PORT"
+    --port "$LISTEN_PORT" \
+    -dev ROCm0 \
+    -ngl 999 \
+    -c "$CTX_SIZE" \
+    -b "$BATCH_SIZE" \
+    -ub "$UBATCH_SIZE" \
+    -fa on \
+    -ctk "$CACHE_TYPE_K" \
+    -ctv "$CACHE_TYPE_V" \
+    -np "$PARALLEL" \
+    -ctxcp "$CTX_CHECKPOINTS" \
+    --cache-ram "$CACHE_RAM" \
+    --cache-prompt \
+    --metrics \
+    --spec-type draft-mtp \
+    --spec-draft-device ROCm0 \
+    --spec-draft-ngl 999 \
+    --spec-draft-type-k f16 \
+    --spec-draft-type-v f16 \
+    --spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
+    --spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
+    --spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
+    --spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
+    --spec-draft-backend-sampling \
+    --temp "$TEMPERATURE" \
+    --top-p "$TOP_P" \
+    --reasoning "$REASONING" \
+    --reasoning-format "$REASONING_FORMAT" \
+    --reasoning-budget -1 \
+    -lv "$VERBOSITY"