Reorganize: tracked DFlash2 archive files -> .AGENTTRASH (repo root)

2026-08-22 15:07:31 -07:00
parent aa410f4439
commit 1f565c08c3
2 changed files with 0 additions and 0 deletions
@@ -0,0 +1,60 @@
+# Tunables for frank-default-large (upstream llama.cpp PR #27342 DFlash2,
+# Vulkan backend, dankclaw, Strix Halo gfx1151).
+#
+# 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.
+#
+# 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). This deployment uses Vulkan, not HIP, but the rule stays for
+# portability.
+
+# Upstream llama.cpp DFlash2 binary (PR #27342, Vulkan build).
+LLAMA_BIN=/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server
+
+# 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, 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
+UBATCH_SIZE=4096
+CACHE_TYPE_K=f16
+CACHE_TYPE_V=f16
+CTX_CHECKPOINTS=16
+CACHE_RAM=8192
+
+# 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, thinking-general).
+TEMPERATURE=0.7
+TOP_P=0.95
+
+# Thinking enabled. deepseek format moves the thinking reasoning into
+# message.reasoning_content (OpenAI-compatible).
+REASONING=on
+REASONING_FORMAT=deepseek
+
+VERBOSITY=4
@@ -0,0 +1,104 @@
+#!/usr/bin/env bash
+# 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: 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 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.
+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/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}"
+: "${CTX_SIZE:=262144}"
+: "${PARALLEL:=1}"
+: "${BATCH_SIZE:=4096}"
+: "${UBATCH_SIZE:=4096}"
+: "${CACHE_TYPE_K:=f16}"
+: "${CACHE_TYPE_V:=f16}"
+: "${CTX_CHECKPOINTS:=16}"
+: "${CACHE_RAM:=8192}"
+: "${SPEC_TYPE:=draft-dflash}"
+: "${SPEC_DRAFT_N_MAX:=8}"
+: "${SPEC_DRAFT_N_MIN:=0}"
+: "${SPEC_DRAFT_P_MIN:=0.0}"
+: "${SPEC_DRAFT_P_SPLIT:=0.10}"
+: "${TEMPERATURE:=0.7}"
+: "${TOP_P:=0.95}"
+: "${REASONING:=on}"
+: "${REASONING_FORMAT:=deepseek}"
+: "${VERBOSITY:=4}"
+
+MODEL="$MODEL_DIR/$MODEL_FILE"
+DRAFT="$MODEL_DIR/$DRAFT_FILE"
+
+if [[ ! -f "$MODEL" ]]; then
+    echo "missing required file: $MODEL" >&2
+    exit 1
+fi
+if [[ ! -f "$DRAFT" ]]; then
+    echo "missing DFlash2 drafter: $DRAFT" >&2
+    exit 1
+fi
+if [[ ! -x "$LLAMA_BIN" ]]; then
+    echo "missing llama-server binary: $LLAMA_BIN" >&2
+    exit 1
+fi
+
+exec "$LLAMA_BIN" \
+    --model "$MODEL" \
+    --alias "$ALIAS" \
+    --host "$BIND_ADDR" \
+    --port "$LISTEN_PORT" \
+    -dev Vulkan0 \
+    -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 "$SPEC_TYPE" \
+    --spec-draft-model "$DRAFT" \
+    --spec-draft-device Vulkan0 \
+    --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" \
+    --temp "$TEMPERATURE" \
+    --top-p "$TOP_P" \
+    --reasoning "$REASONING" \
+    --reasoning-format "$REASONING_FORMAT" \
+    --reasoning-budget -1 \
+    -lv "$VERBOSITY"