frank-default-large: swap to caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP
Replace the retired kingjones ROCmFP4 STRIX MTP payload on Dankclaw with cafonz/Qwen3.8-27B-ROCmI4-MTP-GGUF (eemin namespace, public), served by the charlie12345/ROCmFPX llama.cpp build (ROCmI4 W4A4, c49ebdbd) on the Strix Halo iGPU. Q4_0_ROCMI4 with an embedded NextN/MTP head (no separate draft file); strict-Qwen MTP n16/p0.60/backend sampling on ROCm0. Binary /home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server; model dir /home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP. Updated serve script + env, ubatch bench, large-config bats test, docs, AGENTS.md.
This commit is contained in:
Frank committed
1 parent
7a8500f6fa
commit
7ca9dc248e
10 files changed
+626
-131
No files matched your search
@@ -1,22 +1,18 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP (dense) as
|
||||
# frank-default-large via the CIRU ROCmFPX llama.cpp runtime on Dankclaw
|
||||
# (Strix Halo gfx1151).
|
||||
# Serve caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded MTP) as
|
||||
# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
|
||||
# (ROCmI4 W4A4) on Dankclaw (Strix Halo gfx1151).
|
||||
#
|
||||
# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
|
||||
# qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) plus the v3 output-K8
|
||||
# runtime patch (commit af0eac6), against the private TheRock ROCm 7.15 SDK
|
||||
# (kept in the retired ling3-ciru venv). The model is the plain ROCmFP4
|
||||
# Q6 AGENT GGUF (no PromptForge .pfs sidecars) with the standalone MTP draft
|
||||
# head mtp-Qwen3.8-27B-Q4_0.gguf. The Qwen-Sharp chat template is applied at
|
||||
# runtime.
|
||||
# Runtime: charlie12345/ROCmFPX pinned at commit
|
||||
# c49ebdbd5c9f01ec242369f9e7f7967855f80cba, built with
|
||||
# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4,
|
||||
# amdclang 22). The model has an embedded NextN/MTP head in the main GGUF, so
|
||||
# a separate draft file is not loaded; the MTP draft runs on ROCm0 with all
|
||||
# layers via --spec-draft-ngl all.
|
||||
#
|
||||
# Spec: dense model -> native MTP draft at n_max 4 (the knee, per the model
|
||||
# card). The draft head is a separate Q4_0 GGUF loaded via --model-draft.
|
||||
#
|
||||
# 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.
|
||||
# The qualified MTP profile is strict Qwen MTP (--spec-mtp-strict-qwen) with
|
||||
# backend sampling, n_max 16, p_min 0.60 (see the model card and the
|
||||
# charlie12345/ROCmFPX ROCMI4 runbook).
|
||||
#
|
||||
# Tunables come from frank-default-large.env in this directory unless
|
||||
# FRANK_LARGE_ENV_FILE overrides that path.
|
||||
@@ -32,30 +28,32 @@ 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}"
|
||||
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
|
||||
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
|
||||
: "${MTP_DRAFT_FILE:=mtp-Qwen3.8-27B-Q4_0.gguf}"
|
||||
: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
|
||||
: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
|
||||
: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
|
||||
: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
|
||||
: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
|
||||
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
|
||||
: "${ROCM_DEVEL:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel}"
|
||||
: "${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}"
|
||||
: "${CTX_SIZE:=262144}"
|
||||
: "${PARALLEL:=1}"
|
||||
: "${BATCH_SIZE:=4096}"
|
||||
: "${UBATCH_SIZE:=4096}"
|
||||
: "${BATCH_SIZE:=512}"
|
||||
: "${UBATCH_SIZE:=256}"
|
||||
: "${NUM_THREADS:=16}"
|
||||
: "${THREAD_BATCH:=32}"
|
||||
: "${CACHE_TYPE_K:=f16}"
|
||||
: "${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}"
|
||||
# Embedded-MTP (qwen35 NextN) qualified profile. The MTP head lives in the main
|
||||
# GGUF, so no standalone draft file is referenced; the draft runs on ROCm0 with all layers.
|
||||
: "${MTP_N_MAX:=16}"
|
||||
: "${MTP_N_MIN:=0}"
|
||||
: "${MTP_P_MIN:=0.60}"
|
||||
: "${SPEC_MTP_STRICT_QWEN:=on}"
|
||||
: "${MTP_BACKEND_SAMPLING:=on}"
|
||||
: "${SPEC_DRAFT_NGL:=all}"
|
||||
: "${TEMPERATURE:=1.0}"
|
||||
: "${TOP_K:=20}"
|
||||
: "${TOP_P:=0.95}"
|
||||
@@ -63,20 +61,20 @@ fi
|
||||
: "${REASONING_FORMAT:=deepseek}"
|
||||
: "${CHAT_TEMPLATE_KWARGS:={}}"
|
||||
: "${VERBOSITY:=4}"
|
||||
# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
|
||||
: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
|
||||
: "${GGML_HIP_ENABLE_UNIFIED_MEMORY:=1}"
|
||||
|
||||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||||
MTP_DRAFT="$MODEL_DIR/$MTP_DRAFT_FILE"
|
||||
MMPROJ="$MODEL_DIR/$MMPROJ_FILE"
|
||||
|
||||
# Plain dense model: no PromptForge .pfs sidecars, no Output-K8 proxy, no IU4
|
||||
# lane. The v3 MTP is driven by the standalone Q4_0 draft head through the
|
||||
# standard draft-mtp path. Unset any leftover PromptForge env lanes.
|
||||
unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
|
||||
unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
|
||||
unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
|
||||
unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
|
||||
unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
|
||||
# Optional vision projector: load it only if the file exists.
|
||||
MMPROJ_ARGS=()
|
||||
if [[ -f "$MMPROJ" ]]; then
|
||||
MMPROJ_ARGS=(--mmproj "$MMPROJ")
|
||||
fi
|
||||
|
||||
for f in "$MODEL" "$MTP_DRAFT" "$MODEL_DIR/$MMPROJ_FILE" "$CHAT_TEMPLATE_FILE"; do
|
||||
for f in "$MODEL" "$CHAT_TEMPLATE_FILE"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "missing required file: $f" >&2
|
||||
exit 1
|
||||
@@ -87,13 +85,22 @@ if [[ ! -x "$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}"
|
||||
# Any leftover PromptForge env lanes from the previous (kingjones/v3) runtime
|
||||
# must stay off; this slot now runs the plain strict-MTP draft-mtp path.
|
||||
unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
|
||||
unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
|
||||
unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
|
||||
unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
|
||||
unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
|
||||
unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true
|
||||
|
||||
# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
|
||||
export HSA_OVERRIDE_GFX_VERSION
|
||||
export GGML_HIP_ENABLE_UNIFIED_MEMORY
|
||||
|
||||
exec "$LLAMA_BIN" \
|
||||
--model "$MODEL" \
|
||||
--mmproj "$MODEL_DIR/$MMPROJ_FILE" \
|
||||
"${MMPROJ_ARGS[@]}" \
|
||||
--chat-template-file "$CHAT_TEMPLATE_FILE" \
|
||||
--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
|
||||
--alias "$ALIAS" \
|
||||
@@ -101,32 +108,34 @@ exec "$LLAMA_BIN" \
|
||||
--port "$LISTEN_PORT" \
|
||||
-dev ROCm0 \
|
||||
-ngl 999 \
|
||||
-np "$PARALLEL" \
|
||||
-t "$NUM_THREADS" \
|
||||
-tb "$THREAD_BATCH" \
|
||||
-c "$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 "$CACHE_RAM" \
|
||||
--cache-prompt \
|
||||
--metrics \
|
||||
--no-mmap \
|
||||
--spec-type draft-mtp \
|
||||
--model-draft "$MTP_DRAFT" \
|
||||
${SPEC_MTP_STRICT_QWEN:+--spec-mtp-strict-qwen} \
|
||||
--spec-draft-device ROCm0 \
|
||||
--spec-draft-ngl 999 \
|
||||
--spec-draft-type-k f16 \
|
||||
--spec-draft-type-v f16 \
|
||||
--spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
|
||||
--spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
|
||||
--spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
|
||||
--spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
|
||||
--spec-draft-ngl "$SPEC_DRAFT_NGL" \
|
||||
--spec-draft-type-k "$CACHE_TYPE_K" \
|
||||
--spec-draft-type-v "$CACHE_TYPE_V" \
|
||||
--spec-draft-n-max "$MTP_N_MAX" \
|
||||
--spec-draft-n-min "$MTP_N_MIN" \
|
||||
--spec-draft-p-min "$MTP_P_MIN" \
|
||||
${MTP_BACKEND_SAMPLING:+--spec-draft-backend-sampling} \
|
||||
--temp "$TEMPERATURE" \
|
||||
--top-k "$TOP_K" \
|
||||
--top-p "$TOP_P" \
|
||||
--reasoning "$REASONING" \
|
||||
--reasoning-format "$REASONING_FORMAT" \
|
||||
--reasoning-budget -1 \
|
||||
-lv "$VERBOSITY"
|
||||
-lv "$VERBOSITY"
|
||||
Reference in new issue
Block a user