diff --git a/.AGENTTRASH/frank-default-large.env.ciru-activefpx-2026-08-21 b/.AGENTTRASH/frank-default-large.env.ciru-activefpx-2026-08-21
new file mode 100644
index 0000000..074e0e4
--- /dev/null
+++ b/.AGENTTRASH/frank-default-large.env.ciru-activefpx-2026-08-21
@@ -0,0 +1,74 @@
+# Tunables for frank-default-large (CIRU llama.cpp, 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.
+#
+# 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).
+# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
+
+# 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=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.
+CTX_SIZE=262144
+PARALLEL=1
+BATCH_SIZE=4096
+UBATCH_SIZE=4096
+CACHE_TYPE_K=f16
+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
+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
+
+# 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
diff --git a/.AGENTTRASH/serve-frank-large.sh.ciru-activefpx-2026-08-21 b/.AGENTTRASH/serve-frank-large.sh.ciru-activefpx-2026-08-21
new file mode 100755
index 0000000..540d449
--- /dev/null
+++ b/.AGENTTRASH/serve-frank-large.sh.ciru-activefpx-2026-08-21
@@ -0,0 +1,120 @@
+#!/usr/bin/env bash
+# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge as frank-default-large
+# via the CIRU ROCmFPX llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
+#
+# 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 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.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
+if [[ -f "$ENV_FILE" ]]; then
+    set -a
+    # shellcheck disable=SC1090
+    source "$ENV_FILE"
+    set +a
+fi
+
+# --- defaults (used when the env file does not set them) -------------------
+: "${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:=52625}"
+: "${CTX_SIZE:=524288}"
+: "${PARALLEL:=2}"
+: "${BATCH_SIZE:=4096}"
+: "${UBATCH_SIZE:=4096}"
+: "${CACHE_TYPE_K:=f16}"
+: "${CACHE_TYPE_V:=f16}"
+: "${CTX_CHECKPOINTS:=16}"
+: "${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}"
+: "${REASONING:=on}"
+: "${REASONING_FORMAT:=deepseek}"
+: "${VERBOSITY:=4}"
+
+MODEL="$MODEL_DIR/$MODEL_FILE"
+export PROMPTFORGE_SIDECAR="$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: $MODEL" >&2
+    exit 1
+fi
+if [[ ! -f "$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
+    echo "missing llama-server binary: $LLAMA_BIN" >&2
+    exit 1
+fi
+
+# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
+export ROCM_PATH="$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 "$MODEL" \
+    --alias "$ALIAS" \
+    --host "$BIND_ADDR" \
+    --port "$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 \
+    --no-mmap \
+    --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"
diff --git a/AGENTS.md b/AGENTS.md
index bbac1d8..73b1653 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -3,23 +3,21 @@
 ## Overview
 
 This project manages deployment scripts for the LLM inference fleet on two
-local machines. Topology (2026-08-18):
+local machines. Topology (2026-08-21):
 
 | Target | Host | Runtime | Service | Model | Port |
 |--------|------|---------|---------|-------|------|
 | Dankserver | dank@dankserver | llama.cpp (upstream b10121) | frank-default-small | HauhauCS Qwen3.6-35B-A3B-Uncensored-Aggressive Q6_K_P + ngram-mod, 36 MoE experts on CPU | 7770 |
-| Dankclaw | dank@dankclaw | CIRU ROCmFPX llama.cpp (ROCm 7.15 SDK in the ling3-ciru venv) | frank-default-large | jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge v2, native MTP, PromptForge DualView, 262K context / 1 slot | 52625 |
+| Dankclaw | dank@dankclaw | llama.cpp PR #27342 DFlash2 (Vulkan RADV) | frank-default-large | unsloth Qwen3.8-27B-UD-Q8_K_XL + z-lab Qwen3.8-27B-DFlash2-Q4_K_M drafter, 262K context / 1 slot | 52625 |
 
 The 2026-08-17 redo retired the pipeline-parallel split and the FastFlowLM
-NPU endpoint. The 2026-08-18 swap retired the vLLM service on Dankclaw; the
-CIRU ROCmFPX llama.cpp runtime now runs on the Strix Halo iGPU (gfx1151).
-A second 2026-08-18 swap renamed the services and restored the Qwen3.6 35B
-A3B Q6_K_P model on Dankserver: Dankserver is now `frank-default-small`
-(Qwen3.6-35B-A3B Q6_K_P + ngram-mod, MoE experts on CPU) and Dankclaw is
-now `frank-default-large` (CIRU Qwen3.8-27B, 262K context / 1 slot). The
-retired Qwen3.8-27B IQ4_XS FastMTP files live in `.AGENTTRASH/`. See
-docs/ciru-activefpx-promptforge.md. The old scripts live in `old/scripts/`
-for reference; they describe the retired PP topology.
+NPU endpoint. The 2026-08-18 swap retired the vLLM service and the CIRU
+ROCmFPX runtime on Dankclaw. On 2026-08-21 `frank-default-large` moved to
+upstream llama.cpp PR #27342 with DFlash2 speculative decoding on the
+Vulkan backend (`Vulkan0`, RADV gfx1151). The retired CIRU AI and IQ4_XS
+files live in `.AGENTTRASH/`. See docs/dflash2-large-vulkan.md. The old
+scripts live in `old/scripts/` for reference; they describe the retired PP
+topology.
 
 **Sibling project:** [../serverAppConfigs](../serverAppConfigs) manages the
 Podman app stack on the same hosts (OpenWebUI, Gitea, observability). Its
@@ -65,7 +63,7 @@ Use `scripts/deploy.sh` to deploy committed changes to a target. It pushes `main
 
 ```
 FRANK_SUDO_PW=... ./scripts/deploy.sh dankserver   # llama.cpp FastMTP, port 7770
-FRANK_SUDO_PW=... ./scripts/deploy.sh dankclaw     # CIRU llama.cpp, port 52625
+FRANK_SUDO_PW=... ./scripts/deploy.sh dankclaw     # DFlash2 llama.cpp, port 52625
 ./scripts/deploy.sh dankserver --dry-run           # preview without changes
 ```
 
@@ -127,23 +125,19 @@ back to a slow path and prefill collapses ~12x (measured 2026-08-17: 95 t/s
 vs 1300+ t/s at an 8K prompt on the 3090). See the HauhauCS HF repo README
 for the base recipe.
 
-### CIRU ROCmFPX llama.cpp (Dankclaw)
+### DFlash2 llama.cpp (Dankclaw, Vulkan)
 
-The CIRU llama-server serves `jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge`
-from `/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server`.
-The runtime is the ciru-ai/ROCmFPX tag `qwen3.8-activefpx-promptforge-v2.3`
-(commit `103af8b41`) built against the private TheRock ROCm 7.15 SDK kept
-in the retired ling3-ciru venv
-(`.venv/lib/python3.12/site-packages/_rocm_sdk_*`). The model card requires
-ROCm 7.15 for the advertised Strix Halo performance; the system ROCm 7.2.4
-selects slower kernels. The serve script exports the 7.15 SDK libraries
-first in `LD_LIBRARY_PATH`.
+The upstream llama.cpp PR #27342 llama-server serves
+`unsloth/Qwen3.8-27B-UD-Q8_K_XL.gguf` with a z-lab DFlash2 drafter
+(`Qwen3.8-27B-DFlash2-Q4_K_M.gguf`) on the Vulkan backend. The binary lives
+at `/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server`. DFlash2
+needs `TOP_K` + `ARGMAX`, which HIP does not implement, so the stack runs on
+`Vulkan0` (RADV, gfx1151). See docs/dflash2-large-vulkan.md.
 
-The model files (v2 GGUF + FFN.pfs + GDN.pfs, ~34.9 GiB) live in
-`/home/dank/models/CIRU-Qwen3.8-27B-ActiveFPX/`. The full build runbook is
-in docs/ciru-activefpx-promptforge.md. The retired vLLM venvs
-(`/home/dank/vllm-venv`, `/home/dank/vllm-vk-venv`) were moved to
-`/home/dank/.AGENTTRASH/` on 2026-08-18.
+The target and drafter live in `/home/dank/models/`. The retired CIRU
+runtime (ROCmFPX v2.3, ROCm 7.15 SDK in the ling3-ciru venv, FFN/GDN
+companions) is archived in `.AGENTTRASH/` and documented in
+circu-activefpx-promptforge.md.
 
 **Env var naming rule still applies:** the HIP runtime reads `TEMP`, `HOST`,
 and `GPU_MAX_HEAP_SIZE`. The serve script passes `--host`/`--port`/`--temp`
@@ -192,7 +186,7 @@ graph TD
 
 - `sudo` on both boxes needs a tty. Remote sudo steps fail non-interactively. Use `echo '<password>' | sudo -S <command>`.
 - Never run `pkill -f` with a pattern that appears in your own command line. It kills your ssh session. Use `pkill -x <exact-name>`.
-- Model load is slow: Dankserver loads the 30.6 GB Q6_K_P through RAM (`--no-mmap`, MoE experts on CPU) in a few minutes cold; Dankclaw CIRU loads the 34.9 GiB ActiveFPX payload in ~5-10 minutes. Health returns 503 while loading. Do not kill the process. `deploy.sh` waits up to 20 minutes on both targets (see `HEALTH_WAIT`).
+- Model load is slow: Dankserver loads the 30.6 GB Q6_K_P through RAM (`--no-mmap`, MoE experts on CPU) in a few minutes cold; Dankclaw DFlash2 loads the 31.4 GB UD-Q8_K_XL + 2.0 GB drafter in ~1 minute with a warm OS page cache and a few minutes cold. Health returns 503 while loading. Do not kill the process. `deploy.sh` waits up to 20 minutes on both targets (see `HEALTH_WAIT`).
 - A client abort and a server release look different in the journal. A client abort logs `W srv stop: cancel task, id_task = N`. A natural stop (EOS or limit) logs only `slot release` with `truncated = 0`. The server never preempts a running generation; when all slots are busy, new tasks defer into a queue. See the 2026-08-13 incident in [docs/deployment.md](docs/deployment.md).
 - Retired hardware history: the Dankserver 35B cuBLAS crash and the DFlash premature-EOS bug are historical; see [docs/dankserver-vram-growth.md](docs/dankserver-vram-growth.md) and [docs/qwen3.8-spec-matrix.md](docs/qwen3.8-spec-matrix.md). The FastFlowLM NPU endpoint is retired; see [docs/FastFlowLM NPU Inference.md](docs/FastFlowLM%20NPU%20Inference.md).
 
diff --git a/docs/deployment.md b/docs/deployment.md
index d06182b..b886f52 100644
--- a/docs/deployment.md
+++ b/docs/deployment.md
@@ -9,7 +9,7 @@ Two servers run LLM inference services. Each server pulls its scripts from this
 | Target | Host | Runtime | Service | Port |
 |--------|------|---------|---------|------|
 | Dankserver | dank@dankserver | upstream llama.cpp (Qwen3.6-35B-A3B Q6_K_P + ngram-mod, MoE on CPU) | frank-default-small | 7770 |
-| Dankclaw | dank@dankclaw | CIRU ROCmFPX llama.cpp (jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge v2, native MTP + PromptForge DualView, 262K ctx / 1 slot) | frank-default-large | 52625 |
+| Dankclaw | dank@dankclaw | upstream llama.cpp PR #27342 DFlash2 (unsloth Qwen3.8-27B-UD-Q8_K_XL + z-lab DFlash2 Q4_K_M drafter, Vulkan, 262K ctx / 1 slot) | frank-default-large | 52625 |
 
 ## Workflow
 
@@ -115,19 +115,19 @@ launches through `scripts/serve-frank-small.sh`, which reads tunables from
 
 ### Dankclaw — frank-default-large
 
-The active service on Dankclaw is the CIRU ROCmFPX llama.cpp runtime serving
-`jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge` (v2 GGUF + FFN/GDN
-companions) under the alias `frank-default-large` on port 52625. It runs
-`/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server` (ROCm
-7.15 SDK in the retired ling3-ciru venv) with native depth-4 MTP
-(`--spec-type draft-mtp`), f16 KV for both K and V, full 262144 context
-(1 slot; concurrent requests queue, the server never preempts a running
-generation), batch 4096 / ubatch 4096, 16
-context checkpoints, 8 GiB
+The active service on Dankclaw is upstream llama.cpp PR #27342 (DFlash2
+support) built with GGML_VULKAN=ON, serving
+`/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL.gguf` (unsloth Dynamic v3.0,
+31.4 GB) under the alias `frank-default-large` on port 52625. It runs
+`/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server` with a
+z-lab DFlash2 drafter (`/home/dank/models/Qwen3.8-27B-DFlash2-Q4_K_M.gguf`,
+block size 8) via `--spec-type draft-dflash`, on the Vulkan (RADV) backend
+(`Vulkan0`, gfx1151, 113942 MiB). f16 KV for both K and V, full 262144
+context (1 slot), batch 4096 / ubatch 4096, 16 context checkpoints, 8 GiB
 prompt cache, and reasoning in deepseek format. The unit file is
 `scripts/frank-default-large.service`. It launches through
 `scripts/serve-frank-large.sh`, which reads tunables from
-`scripts/frank-default-large.env`. See [[ciru-activefpx-promptforge]].
+`scripts/frank-default-large.env`. See [[dflash2-large-vulkan]].
 
 ## Validation
 
diff --git a/docs/dflash2-large-vulkan.md b/docs/dflash2-large-vulkan.md
new file mode 100644
index 0000000..5b42bc7
--- /dev/null
+++ b/docs/dflash2-large-vulkan.md
@@ -0,0 +1,170 @@
+---
+type: reference
+title: DFlash2 on Dankclaw (frank-default-large)
+description: unsloth Qwen3.8-27B-UD-Q8_K_XL served by upstream llama.cpp PR #27342 with a z-lab DFlash2 drafter on the Vulkan backend. Install runbook and the frank-default-large service.
+tags:
+  - llama.cpp
+  - vulkan
+  - dankclaw
+  - gfx1151
+  - dflash
+  - dflash2
+  - speculative-decoding
+timestamp: 2026-08-21
+---
+
+# DFlash2 on Dankclaw (frank-default-large)
+
+`frank-default-large` (port 52625) serves
+`unsloth/Qwen3.8-27B-UD-Q8_K_XL` with a DFlash2 drafter from z-lab. The
+runtime is upstream llama.cpp PR #27342 built with `GGML_VULKAN=ON`.
+This deployment replaced the CIRU HIP runtime on 2026-08-21.
+
+## Why Vulkan
+
+DFlash2 selects its draft candidates with a lightweight path selector
+built on the `TOP_K` and `ARGMAX` graph ops. The HIP backend does not
+implement `TOP_K`. That is why the retired CIRU setup routed the MTP
+draft around it with `LLAMA_MTP_CPU_ARGMAX_FASTPATH`.
+
+The PR reference fork (Nathanw1014/strix-halo-llamacpp) validated DFlash2
+on this exact gfx1151 through Vulkan (RADV). Its `test-backend-ops` passed
+the new graph ops:
+
+| Op | Cases |
+|----|-------|
+| TOP_K | 445 |
+| CONCAT | 193 |
+| PAD | 28 |
+| REPEAT | 18 |
+| FILL | 4 |
+
+The whole stack (target + drafter) runs on `Vulkan0`.
+
+## What Runs
+
+| Artifact | Repo / File | Size |
+|----------|-------------|------|
+| Target | `unsloth/Qwen3.8-27B-GGUF` `Qwen3.8-27B-UD-Q8_K_XL.gguf` | 31.4 GB |
+| Drafter | `z-lab/Qwen3.8-27B-DFlash2-GGUF` `Qwen3.8-27B-DFlash2-Q4_K_M.gguf` | 2.0 GB |
+| Runtime | upstream llama.cpp PR #27342, GGML_VULKAN=ON | - |
+
+The target was already on disk. The drafter was added for this deploy.
+Both live in `/home/dank/models/`.
+
+## Drafter Hyperparameters
+
+Read from the drafter GGUF metadata:
+
+| Parameter | Value |
+|-----------|-------|
+| `dflash.block_count` | 5 |
+| `dflash.block_size` | 8 |
+| `dflash.conv_kernel_size` | 2 |
+| `dflash.conv_group_size` | 16 |
+| `dflash.selector_rank` | 256 |
+| `dflash.selector_top_k` | 16 |
+| `dflash.context_length` | 262144 |
+| `dflash.embedding_length` | 5120 |
+| architecture | `dflash` |
+
+The target and drafter share the Qwen3.8 architecture
+(`qwen35`, dense 27B, vocab 248320), so the drafter inherits the target
+tokenizer and LM head.
+
+## Build Runbook (2026-08-21)
+
+Performed on Dankclaw.
+
+1. In `/home/dank/llama.cpp`, register the `ggml` remote and fetch the PR
+   head:
+   ```
+   git -C /home/dank/llama.cpp remote add ggml https://github.com/ggml-org/llama.cpp.git
+   git -C /home/dank/llama.cpp fetch ggml pull/27342/head:pr-27342
+   ```
+2. Add a detached worktree that does not disturb the running build:
+   ```
+   git -C /home/dank/llama.cpp worktree add --detach /home/dank/llama.cpp-dflash2 pr-27342
+   ```
+3. Configure with Vulkan only (glslang and `glslc` must be installed):
+   ```
+   cmake -B /home/dank/llama.cpp-dflash2/build-dflash2 -G Ninja \
+     -DGGML_VULKAN=ON -DGGML_HIP=OFF -DGGML_CUDA=OFF -DGGML_METAL=OFF \
+     -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release \
+     -DLLAMA_BUILD_SERVER=ON -DLLAMA_BUILD_WEBUI=OFF
+   ```
+4. Build the server:
+   ```
+   cmake --build /home/dank/llama.cpp-dflash2/build-dflash2 --target llama-server -j16
+   ```
+5. Verify the Vulkan device:
+   ```
+   /home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server --list-devices
+   ```
+   Output: `Vulkan0: AMD Radeon Graphics (RADV STRIX_HALO)`.
+
+```mermaid
+graph TD
+    A[Fetch PR #27342 head] --> B[Worktree on DFlash2 head]
+    B --> C[Configure Vulkan build]
+    C --> D[Build llama-server]
+    D --> E[Verify Vulkan0 device]
+    E --> F[Add DFlash2 drafter]
+    F --> G[Swap frank-default-large]
+    G --> H[Health check + completion]
+```
+
+## Service
+
+- Unit: `frank-default-large.service`, port 52625
+- Script: `scripts/serve-frank-large.sh`, env `scripts/frank-default-large.env`
+- Binary: `/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server`
+
+### Launch profile
+
+- 262144 context (native max), 1 slot, f16 KV (~16 GiB), 16 context
+  checkpoints, 8 GiB prompt cache
+- DFlash2 draft, block size 8, device Vulkan0, drafter fully offloaded
+- `--spec-type draft-dflash --spec-draft-n-max 8`
+  (clamped to block size 8 - 1 = 7 at runtime)
+- `--temp 0.7 --top-p 0.95`, reasoning on (`--reasoning-format deepseek`)
+- `--no-mmap`, flash attention `-fa on`, `--metrics`
+
+### Required environment
+
+No PromptForge variables are needed. The `TEMP`, `HOST`, and
+`GPU_MAX_HEAP_SIZE` naming rule still applies for portability, even though
+this build uses Vulkan, not HIP.
+
+## Validation
+
+The smoke test on 2026-08-21 used a scratch port (52626) and confirmed:
+
+- Both models load and the server reports healthy.
+- A chat completion returns reasoning and content.
+- The DFlash2 drafter engaged:
+  `draft-dflash: #gen drafts = 11, #acc drafts = 10, #mean acc len = 5.27`.
+- The per-position acceptance curve decays along the block
+  `(0.909, 0.818, 0.727, 0.545, 0.545, 0.364, 0.364)`, as expected.
+
+The published mean acceptance for the Q4_K_M drafter is ~5.39, so 5.27
+is close.
+
+## Operational Notes
+
+- Health: `curl http://127.0.0.1:52625/health`. Returns 503 while loading.
+- Model load takes about a minute with a warm OS page cache (31 GB target)
+  and longer on a cold cache. Do not kill the process during warmup.
+- `deploy.sh dankclaw` waits 20 minutes for health.
+- The Vulkan device reports 113942 MiB. rocm-smi reports the 64 GiB
+  unified-memory budget. Trust the runtime for the addressable SVM pool.
+- The MTP head of the target GGUF is ignored (`--spec-type draft-dflash`
+  replaces it). The load log warns about unused MTP tensors; this is normal.
+
+## See Also
+
+- [[DFlash DSpark Speculative Decoding]] — DFlash/DSpark design and history
+- [[ciru-activefpx-promptforge]] — the retired CIRU runtime (archived)
+- [[deployment]] — the deployment and update process
+- [[qwen3.8-strix-optimizations]] — llama.cpp Optimizations on this iGPU
+- [[index]] — knowledge base index
diff --git a/docs/index.md b/docs/index.md
index 8df3bf3..4cd4a71 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,8 +1,8 @@
 # vLLM Scripts — Knowledge Base
 
 Documentation for the LLM inference fleet on two local machines
-(2026-08-18): upstream llama.cpp on Dankserver (frank-default-small) and
-CIRU ROCmFPX llama.cpp on Dankclaw (frank-default-large).
+(2026-08-21): upstream llama.cpp on Dankserver (frank-default-small) and
+upstream llama.cpp PR #27342 DFlash2 on Dankclaw (frank-default-large).
 
 ## Deployment Topology
 
@@ -19,10 +19,11 @@ ngram-mod, 36 MoE experts on CPU, 700K ctx]
 
     subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
         D[gfx1151 iGPU 64 GiB unified memory]
-        E[CIRU ROCmFPX llama.cpp
+        E[upstream llama.cpp PR #27342 DFlash2, Vulkan
 frank-default-large, port 52625]
-        F[jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge
-262K ctx / 1 slot, native MTP, PromptForge DualView]
+        F[unsloth Qwen3.8-27B-UD-Q8_K_XL +
+z-lab Qwen3.8-27B-DFlash2-Q4_K_M drafter
+262K ctx / 1 slot, DFlash2 spec]
         D --> E --> F
     end
 
@@ -41,16 +42,21 @@ frank-default-large, port 52625]
 
 - [[deployment]] — deploy and update process for both servers
 - [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
-- [[ciru-activefpx-promptforge]] — the CIRU runtime on Dankclaw
-  (frank-default-large)
+- [[dflash2-large-vulkan]] — the DFlash2 runtime on Dankclaw
+  (frank-default-large, Vulkan)
 - [[Dankserver]] — the upstream llama.cpp box (frank-default-small)
-- [[Dankclaw]] — the CIRU ROCmFPX box (frank-default-large)
+- [[Dankclaw]] — the DFlash2 Vulkan box (frank-default-large)
 
-## CIRU Reference (Dankclaw)
+## DFlash2 Reference (Dankclaw)
 
-- [[ciru-activefpx-promptforge]] — model, ROCm 7.15 toolchain, build,
+- [[dflash2-large-vulkan]] — DFlash2 model, Vulkan build, build runbook,
   and the frank-default-large service
 
+## CIRU Reference (retired)
+
+- [[ciru-activefpx-promptforge]] — the retired CIRU ROCmFPX runtime
+  (archived in .AGENTTRASH, 2026-08-21)
+
 ## vLLM Reference (historical)
 
 - [[VLLM Overview]] — installation, CLI, API, architecture, quantization, parallelism
diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 074e0e4..cb4eabc 100644
--- a/scripts/frank-default-large.env
+++ b/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
\ No newline at end of file
diff --git a/scripts/frank-default-large.service b/scripts/frank-default-large.service
index 70cdd45..0cd5561 100644
--- a/scripts/frank-default-large.service
+++ b/scripts/frank-default-large.service
@@ -1,5 +1,5 @@
 [Unit]
-Description=CIRU llama.cpp Qwen3.8-27B ActiveFPX PromptForge MTP (dankclaw, frank-default-large)
+Description=llama.cpp DFlash2 Qwen3.8-27B UD-Q8_K_XL + Q4_K_M drafter (dankclaw, frank-default-large)
 After=network-online.target
 Wants=network-online.target
 
diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh
index 540d449..bb1217b 100755
--- a/scripts/serve-frank-large.sh
+++ b/scripts/serve-frank-large.sh
@@ -1,16 +1,15 @@
 #!/usr/bin/env bash
-# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge as frank-default-large
-# via the CIRU ROCmFPX llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
+# Serve unsloth/Qwen3.8-27B-UD-Q8_K_XL as frank-default-large with a
+# z-lab DFlash2 drafter (Qwen3.8-27B-DFlash2-Q4_K_M) on the Vulkan backend.
 #
-# 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.
+# Runtime: upstream llama.cpp PR #27342 (DFlash2 support) built with
+# GGML_VULKAN=ON for the Strix Halo gfx1151 (RADV). DFlash2 selects its
+# candidates through TOP_K + ARGMAX ops that the HIP backend does not
+# implement, so the whole stack runs on Vulkan0.
 #
-# 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.
+# The target and the drafter share the Qwen3.8 arch. DFlash is lossless
+# under strict rejection sampling. --spec-draft-n-max clamps to the drafter's
+# trained block size (8).
 #
 # Tunables come from frank-default-large.env in this directory unless
 # FRANK_LARGE_ENV_FILE overrides that path.
@@ -26,26 +25,23 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
-: "${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}"
+: "${LLAMA_BIN:=/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server}"
+: "${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}"
 : "${LISTEN_PORT:=52625}"
-: "${CTX_SIZE:=524288}"
-: "${PARALLEL:=2}"
+: "${CTX_SIZE:=262144}"
+: "${PARALLEL:=1}"
 : "${BATCH_SIZE:=4096}"
 : "${UBATCH_SIZE:=4096}"
 : "${CACHE_TYPE_K:=f16}"
 : "${CACHE_TYPE_V:=f16}"
 : "${CTX_CHECKPOINTS:=16}"
 : "${CACHE_RAM:=8192}"
-: "${SPEC_DRAFT_N_MAX:=4}"
+: "${SPEC_TYPE:=draft-dflash}"
+: "${SPEC_DRAFT_N_MAX:=8}"
 : "${SPEC_DRAFT_N_MIN:=0}"
 : "${SPEC_DRAFT_P_MIN:=0.0}"
 : "${SPEC_DRAFT_P_SPLIT:=0.10}"
@@ -56,22 +52,14 @@ fi
 : "${VERBOSITY:=4}"
 
 MODEL="$MODEL_DIR/$MODEL_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
+DRAFT="$MODEL_DIR/$DRAFT_FILE"
 
 if [[ ! -f "$MODEL" ]]; then
     echo "missing required file: $MODEL" >&2
     exit 1
 fi
-if [[ ! -f "$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: $PROMPTFORGE_GDN_SIDECAR" >&2
+if [[ ! -f "$DRAFT" ]]; then
+    echo "missing DFlash2 drafter: $DRAFT" >&2
     exit 1
 fi
 if [[ ! -x "$LLAMA_BIN" ]]; then
@@ -79,16 +67,12 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 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" \
     --alias "$ALIAS" \
     --host "$BIND_ADDR" \
     --port "$LISTEN_PORT" \
-    -dev ROCm0 \
+    -dev Vulkan0 \
     -ngl 999 \
     -c "$CTX_SIZE" \
     -b "$BATCH_SIZE" \
@@ -102,8 +86,9 @@ exec "$LLAMA_BIN" \
     --cache-prompt \
     --metrics \
     --no-mmap \
-    --spec-type draft-mtp \
-    --spec-draft-device ROCm0 \
+    --spec-type "$SPEC_TYPE" \
+    --spec-draft-model "$DRAFT" \
+    --spec-draft-device Vulkan0 \
     --spec-draft-ngl 999 \
     --spec-draft-type-k f16 \
     --spec-draft-type-v f16 \
@@ -111,10 +96,9 @@ exec "$LLAMA_BIN" \
     --spec-draft-n-min "$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 "$VERBOSITY"
+    -lv "$VERBOSITY"
\ No newline at end of file