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.

scripts/frank-default-large.env

@@ -1,62 +1,72 @@
-# Tunables for frank-default-large (llama.cpp, dankserver, RTX 3090).
+# Tunables for frank-default-large (CIRU llama.cpp, dankclaw, Strix Halo
+# gfx1151).
 #
-# Runtime: patched llama-server (HauhauCS FastMTP build) serving
-# HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF IQ4_XS with
-# the FastMTP 32K draft sidecar and the ngram-mod fallback. Single machine,
-# no pipeline split. Alias frank-default-large, port 7770.
+# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
+# qwen3.8-activefpx-promptforge-v2.3 serving
+# jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge (v2). ActiveFPX compact
+# GGUF with PromptForge companions for CIRU DualView prompt acceleration and
+# native depth-4 MTP. Alias frank-default-large, port 52625.
+#
+# This runtime replaced the retired vLLM service that previously occupied
+# this slot. See docs/ciru-activefpx-promptforge.md.
 #
 # 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).
-# This box is NVIDIA/CUDA, but the rule still applies to keep the env files
-# portable.
+# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
 
-# Model files (downloaded to this directory from the HF repo).
-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
-# Patched llama.cpp binary. The FastMTP sidecar needs the patch; see AGENTS.md.
-# REQUIRED build flags: -DGGML_CUDA_FA=ON -DGGML_CUDA_FA_ALL_QUANTS=ON.
-# Without FA_ALL_QUANTS the q8_0 KV + flash attention fall back to a slow
-# path and prefill collapses ~12x (95 t/s vs 1300+ t/s at 8K prompt,
-# measured 2026-08-17). Do not rebuild without it.
-LLAMA_BIN=/home/dank/llama.cpp-fastmtp/build/bin/llama-server
+# CIRU llama-server binary (ROCmFPX v2.3 build, see docs/ciru runtime page).
+# Built against the private TheRock ROCm 7.15 SDK kept in the retired
+# ling3-ciru venv. ROCm 7.15 is required for the advertised Strix Halo
+# performance; the system ROCm 7.2.4 selects slower/fallback kernels.
+LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
+
+# Model files. The three-file payload (v2 GGUF + FFN + GDN) enables CIRU
+# DualView prompt acceleration; omit the two .pfs files to run the GGUF alone
+# and save ~19.7 GiB of memory at the cost of prompt throughput.
+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 7.15 SDK paths (inside the retired ling3-ciru venv). The serve script
+# exports ROCM_PATH and LD_LIBRARY_PATH from these so the 7.15 libraries
+# precede any system ROCm 7.2.4.
+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
+LISTEN_PORT=52625
 
-# Context, single slot. 131072 (128K) leaves ~1.4 GiB VRAM headroom on the
-# 3090 with IQ4_XS + FastMTP + K q8_0 / V f16 KV. Lower to 122880 (120K) for
-# ~1.8 GiB headroom. KV per token = 16 attention layers x 4 KV heads x 256
-# dim: K q8_0 (1088 B/token) + V f16 (2048 B/token) = 3136 B/token/layer.
-CTX_SIZE=131072
-PARALLEL=1
-
-# Speculative decoding. FastMTP (MTP depth 2) with the ngram-mod fallback.
-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
-
-# KV quantization on GPU: K q8_0 + V f16 (user request: K=8, V=16).
-CACHE_TYPE_K=q8_0
-CACHE_TYPE_V=f16
-
-# Batch sizing (user request).
+# Serving: 256K context (native max, n_ctx_train = 262144), 2 slots, f16 KV,
+# context checkpoints, prompt cache. Native MTP depth-4. The Strix Halo is
+# unified memory; the addressable pool is 96 GiB (VRAM is a pointer). KV at
+# 262144 x 2 slots is ~32 GiB (64 KiB/cell, 16 full-attn layers); total
+# sits well inside the 96 GiB pool.
+CTX_SIZE=262144
+PARALLEL=2
 BATCH_SIZE=2048
-UBATCH_SIZE=1024
+UBATCH_SIZE=2048
+CACHE_TYPE_K=f16
+CACHE_TYPE_V=f16
+CTX_CHECKPOINTS=32
+CACHE_RAM=8192
 
-# Sampling - Qwen3.8 thinking-mode defaults.
-TEMPERATURE=1.0
-TOP_K=20
+# Native MTP draft (depth-4, greedy, ROCm-safe CPU argmax fast path).
+SPEC_DRAFT_N_MAX=4
+SPEC_DRAFT_N_MIN=0
+SPEC_DRAFT_P_MIN=0.0
+SPEC_DRAFT_P_SPLIT=0.10
+
+# Sampling (model card defaults).
+TEMPERATURE=0.7
 TOP_P=0.95
-MIN_P=0.0
 
-THREADS=8
-THREADS_HTTP=1
+# Thinking enabled (user request, 2026-08-18). deepseek format moves the
+# <think> reasoning into message.reasoning_content (OpenAI-compatible);
+# none would leave the thought tags unparsed in content.
+REASONING=on
+REASONING_FORMAT=deepseek
 
 VERBOSITY=4