Swap frank-default-large to DFlash2 on Vulkan (PR #27342)

Replace the retired CIRU ROCmFPX runtime with upstream llama.cpp PR #27342
DFlash2 on the Vulkan backend:

- Target: unsloth Qwen3.8-27B-UD-Q8_K_XL.gguf (31.4 GB, already on disk)
- Drafter: z-lab Qwen3.8-27B-DFlash2-Q4_K_M.gguf (block size 8, top-k 16)
- Runtime: /home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server
  (GGML_VULKAN=ON; HIP lacks TOP_K so the stack runs on Vulkan0/RADV)
- spec: --spec-type draft-dflash --spec-draft-n-max 8 (clamps to 7)

Validated 2026-08-21 on scratch port 52626: mean acceptance 5.27,
health + reasoning completion OK.

Archive the retired CIRU .env/.serve script in .AGENTTRASH.
Update deployment.md, index.md, AGENTS.md; add docs/dflash2-large-vulkan.md.

scripts/frank-default-large.env

@@ -1,51 +1,36 @@
-# Tunables for frank-default-large (CIRU llama.cpp, dankclaw, Strix Halo
-# gfx1151).
+# Tunables for frank-default-large (upstream llama.cpp PR #27342 DFlash2,
+# Vulkan backend, dankclaw, Strix Halo gfx1151).
 #
-# 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.
+# Runtime: llama.cpp PR #27342 built with GGML_VULKAN=ON serving
+# unsloth/Qwen3.8-27B-UD-Q8_K_XL (target) with a z-lab DFlash2 drafter
+# (Qwen3.8-27B-DFlash2-Q4_K_M). Target at 31.4 GB, DFlash2 drafter at 2.0 GB.
+# Alias frank-default-large, port 52625.
 #
-# This runtime replaced the retired vLLM service that previously occupied
-# this slot. See docs/ciru-activefpx-promptforge.md.
+# DFlash2 runs on the Vulkan (RADV) backend. Its candidate selector needs
+# TOP_K + ARGMAX, which the HIP backend does not implement. This replaced
+# the CIRU HIP runtime on 2026-08-21. See docs/dflash2-large-vulkan.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).
-# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
+# 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 deployment uses Vulkan, not HIP, but the rule stays for
+# portability.
 
-# 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
+# Upstream llama.cpp DFlash2 binary (PR #27342, Vulkan build).
+LLAMA_BIN=/home/dank/llama.cpp-dflash2/build-dflash2/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
+# Model files. The target (UD-Q8_K_XL) was already on disk; the DFlash2
+# drafter was added for this deployment. Both live in /home/dank/models.
+MODEL_DIR=/home/dank/models
+MODEL_FILE=Qwen3.8-27B-UD-Q8_K_XL.gguf
+DRAFT_FILE=Qwen3.8-27B-DFlash2-Q4_K_M.gguf
 
 ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=52625
 
-# Serving: full native 262144 context (n_ctx_train), 1 slot (user request
-# 2026-08-19: parallel slots degraded performance). -c is the TOTAL
-# context; with PARALLEL=1 it equals the per-slot context. Concurrent
-# requests queue on the single slot; the server never preempts a running
-# generation. f16 KV, context checkpoints, prompt cache, native MTP
-# depth-4. The Strix Halo is unified memory; rocm-smi reports the 64 GiB
-# budget. KV at 262144 x 64 KiB/cell is ~16 GiB.
+# Serving: full native 262144 context, 1 slot. The Vulkan device reports
+# 113942 MiB; KV at 262144 x 64 KiB/cell is ~16 GiB. rocm-smi reports the
+# 64 GiB budget; trust the runtime for the addressable SVM pool.
 CTX_SIZE=262144
 PARALLEL=1
 BATCH_SIZE=4096
@@ -55,20 +40,21 @@ CACHE_TYPE_V=f16
 CTX_CHECKPOINTS=16
 CACHE_RAM=8192
 
-# Native MTP draft (depth-4, greedy, ROCm-safe CPU argmax fast path).
-SPEC_DRAFT_N_MAX=4
+# DFlash2 speculative decoding. The drafter's trained block size is 8;
+# SPEC_DRAFT_N_MAX clamps to it. TOP_K selector (top 16 candidates).
+SPEC_TYPE=draft-dflash
+SPEC_DRAFT_N_MAX=8
 SPEC_DRAFT_N_MIN=0
 SPEC_DRAFT_P_MIN=0.0
 SPEC_DRAFT_P_SPLIT=0.10
 
-# Sampling (model card defaults).
+# Sampling (model card defaults, thinking-general).
 TEMPERATURE=0.7
 TOP_P=0.95
 
-# 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.
+# Thinking enabled. deepseek format moves the thinking reasoning into
+# message.reasoning_content (OpenAI-compatible).
 REASONING=on
 REASONING_FORMAT=deepseek
 
-VERBOSITY=4
+VERBOSITY=4