fleet redo 2026-08-17: retire PP+NPU, new topology

- Move all previous scripts to old/scripts/ (retired PP/NPU-era)
- frank-default-large: llama.cpp FastMTP on dankserver (HauhauCS
  Qwen3.8-27B IQ4_XS + FastMTP 32K draft + ngram-mod, K q8_0/V f16,
  128K ctx, batch 2048/ubatch 1024, port 7770)
- frank-default-small: vLLM ROCm on dankclaw (Avesed Qwen3.6-35B-A3B
  INT8 W8A8, full 262144 ctx, no KV quant, 4 seqs, batch 16384,
  ngram spec, port 52625)
- retarget deploy.sh (dankserver/dankclaw, inline sudo, no helpers)
- docs: deployment + index + AGENTS.md + README for new topology,
  superseded banners on retired docs, add frank-redo-2026-08-17 runbook

scripts/frank-default-large.env

@@ -1,88 +1,58 @@
-# Head tunables — Qwen3.8-27B pipeline-parallel head (Dankclaw).
+# Tunables for frank-default-large (llama.cpp, dankserver, RTX 3090).
 #
-# The head is the LOCAL side of the split. It runs llama-server (b10433,
-# HIP+Vulkan+RPC build in /home/dank/llama.cpp/build) with --rpc pointing at
-# the worker on Dankserver. The model file lives on this machine only; the
-# worker receives its tensor share over the network at load time.
+# 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.
 #
-# CRITICAL: this script must NOT pass --device. When --device is set,
-# llama.cpp uses exactly that device list and silently drops the RPC device
-# (src/llama.cpp llama_prepare_model_devices). Default device selection
-# inserts RPC servers at the FRONT of the device list, so the split becomes
-# [RPC0, iGPU] and --tensor-split index 0 is the worker.
-#
-# WARNING: do not name any variable here TEMP, HOST, or GPU_MAX_HEAP_SIZE
-# (HIP runtime collision, see the 2026-08-13 TEMP incident).
+# 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.
+
+# 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.
+LLAMA_BIN=/home/dank/llama.cpp-fastmtp/build/bin/llama-server
 
-MODEL_DIR=/home/dank/models
-MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_K.gguf
-HEAD_BIN=/home/dank/llama.cpp/build/bin/llama-server
 ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 
-# Comma-separated RPC endpoints (host:port). One worker here.
-RPC_SERVERS=192.168.0.235:50052
-
-# Model split fractions, one per device in order [RPC0, iGPU].
-# 0.68,0.32 = 45 of 65 blocks on the 3090 (blocks 0-44) - the maximum
-# for the Q6_K + q8_0/f16 KV config, measured 2026-08-17 phase 2:
-#  - KV per FA layer = 784 MiB (K 1088 B/token + V 2048 B/token @262144)
-#  - weights(f) = 20334 MB layer pool x f (GGUF scan, exact); embd on
-#    the head side (RPC0 buffer observed 10429.88 MiB at f=0.53)
-#  - KV-per-device count = round(f x 66) layers -> 45 layers = 11 FA
-#    (3..43) -> 8624 MiB. 46 layers (f>=0.7045) still 11 FA but margin
-#    drops to ~0.4 GiB; 48 layers (f>=0.7197) adds FA block 47 -> KV
-#    9408 -> OOM by ~0.85 GiB.
-# Predicted: 13430 (weights) + 8624 (KV) + ~530 (RS) + 189 (compute) =
-# ~22773 MiB -> ~0.7 GiB free. Draft model runs on ROCm0 only (measured
-# phase 1: 1718 MiB, no worker impact).
-TENSOR_SPLIT=0.68,0.32
-
-# Context pool. 262144 total = 1 parallel slot x 262144 per slot
-# (n_ctx_seq = n_ctx / n_seq_max, llama-context.cpp:293).
-CTX_SIZE=262144
+# 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. MTP with the STANDALONE draft head (the Q6_K
-# model has no bundled MTP head; the repo ships the draft sidecar) + the
-# ngram-mod fallback. Set SPEC_NONE=1 for a raw baseline.
-SPEC_NONE=0
+# Speculative decoding. FastMTP (MTP depth 2) with the ngram-mod fallback.
 SPEC_DEFAULT=1
 MTP=1
-SPEC_DRAFT_N_MAX=4
-# Standalone MTP draft head (Q8_0 MTP-only sidecar from the same repo).
-SPEC_DRAFT_MODEL=/home/dank/models/Qwen3.8-27B-Uncensored-draft-Q8_0.gguf
+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 on GPU: K q8_0 + V f16 (mismatched, 16 full-attention layers x 4
-# heads x 256 dim: K = 1088 B/token, V = 2048 B/token -> 3136 B/token ->
-# 784 MiB per FA layer at 262144, 12.25 GiB total). Mismatched K/V with
-# Flash Attention requires the GGML_CUDA_FA_ALL_QUANTS rebuild (2026-08-17:
-# head HIP + worker CUDA at 9b05354ec). Do not revert the binaries without
-# also reverting this.
+# 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: production-verified values (2026-08-14).
-BATCH_SIZE=8192
-UBATCH_SIZE=256
+# Batch sizing (user request).
+BATCH_SIZE=2048
+UBATCH_SIZE=1024
 
-# Sampling — Qwen3.8 thinking-mode defaults.
+# Sampling - Qwen3.8 thinking-mode defaults.
 TEMPERATURE=1.0
 TOP_K=20
 TOP_P=0.95
 MIN_P=0.0
 
-THREADS=12
+THREADS=8
 THREADS_HTTP=1
 
-# 4 (info): clean journal for interactive use. Raise to 10 only when
-# debugging the layer split (the per-layer assignment lines are debug-level).
 VERBOSITY=4
-
-# 1: --direct-io model load. Required in practice for large models loaded
-# over RPC (load hangs otherwise; visorcraft Strix RPC finding).
-DIRECT_IO=1