Swap LLM fleet to Ornith CRACK (small) and kingjones ROCmFP4 STRIX MTP (large); apply Qwen-Sharp chat template
- frank-default-small (Dankserver): Ornith-1.5-35B-A3B-CRACK Q8_0, bundled native draft-mtp (n_max 4), MoE expert FFN tensors pinned to CPU via an explicit --override-tensor \.ffn_(up|down|gate|gate_up)_(ch|)exps=CPU (replaces --n-cpu-moe), Qwen-Sharp chat template. - frank-default-large (Dankclaw): kingjones Qwen3.8-27B-Uncensored-Q6_0 ROCmFP4 AGENT dense GGUF, standalone mtp-Qwen3.8-27B-Q4_0 draft head (--model-draft, draft-mtp n_max 4), Qwen-Sharp chat template. Drop the retired PromptForge .pfs sidecar lanes. - Track scripts/chat-template.jinja (v22.4.0 Sharp) and apply via --chat-template-file on both services. - Docs: new kingjones-strix-mtp and dealign-ornith-crack runbook pages; update index, deployment, and both system specs; models.json names. Smoke-tested both models on the real hardware on scratch ports before commit: model loads, MTP draft attaches, Sharp template applies, chat completion returns.
This commit is contained in:
Frank committed
1 parent
189934af15
commit
4462aa992c
14 files changed
+827
-156
No files matched your search
@@ -1,19 +1,22 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge (v3) as
|
||||
# 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).
|
||||
#
|
||||
# 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 (runtime/qwen38-v3-output-k8-runtime.patch, commit af0eac6 on
|
||||
# Dankclaw) against the private TheRock ROCm 7.15 SDK (kept in the retired
|
||||
# ling3-ciru venv). The model is the v3 GGUF with the full-W8 PromptForge
|
||||
# companion views (FFN/GDN .pfs), the Output-K8 draft proxy, and the BF16
|
||||
# vision projector. Native depth-4 MTP speculative decoding.
|
||||
# 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.
|
||||
#
|
||||
# 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. An older system ROCm must not precede them.
|
||||
# 7.15 SDK libraries first.
|
||||
#
|
||||
# Tunables come from frank-default-large.env in this directory unless
|
||||
# FRANK_LARGE_ENV_FILE overrides that path.
|
||||
@@ -30,20 +33,19 @@ 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-v3}"
|
||||
: "${MODEL_FILE:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-v3-Q8-FFNEQ-LateQ6.gguf}"
|
||||
: "${FFN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-FFN.pfs}"
|
||||
: "${GDN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-GDN.pfs}"
|
||||
: "${OUTPUT_K8_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-Output-K8.pfs}"
|
||||
: "${MMPROJ_FILE:=Qwen3.8-27B-mmproj-BF16.mmproj}"
|
||||
: "${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}"
|
||||
: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
|
||||
: "${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:=524288}"
|
||||
: "${PARALLEL:=2}"
|
||||
: "${CTX_SIZE:=262144}"
|
||||
: "${PARALLEL:=1}"
|
||||
: "${BATCH_SIZE:=4096}"
|
||||
: "${UBATCH_SIZE:=4096}"
|
||||
: "${CACHE_TYPE_K:=f16}"
|
||||
@@ -54,30 +56,27 @@ fi
|
||||
: "${SPEC_DRAFT_N_MIN:=0}"
|
||||
: "${SPEC_DRAFT_P_MIN:=0.0}"
|
||||
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
|
||||
: "${TEMPERATURE:=0.7}"
|
||||
: "${TEMPERATURE:=1.0}"
|
||||
: "${TOP_K:=20}"
|
||||
: "${TOP_P:=0.95}"
|
||||
: "${REASONING:=on}"
|
||||
: "${REASONING_FORMAT:=deepseek}"
|
||||
: "${CHAT_TEMPLATE_KWARGS:={}}"
|
||||
: "${VERBOSITY:=4}"
|
||||
|
||||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||||
export PROMPTFORGE_SIDECAR="$MODEL_DIR/$FFN_PFS"
|
||||
export PROMPTFORGE_GDN_SIDECAR="$MODEL_DIR/$GDN_PFS"
|
||||
# v3 qualified runtime: Output-K8 draft proxy + small-row W8 prompt route.
|
||||
export PROMPTFORGE_MODE="m2048_fused_tail1476"
|
||||
export GGML_CUDA_GRAPH_OPT=0
|
||||
export PROMPTFORGE_ENABLE_SMALLM_W8=1
|
||||
export PROMPTFORGE_MTP_OUTPUT_K8=1
|
||||
export PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE=0
|
||||
export PROMPTFORGE_MTP_OUTPUT_K8_PROXY="$MODEL_DIR/$OUTPUT_K8_PFS"
|
||||
# The qualified v3 profile disables the CPU argmax draft fast path; the
|
||||
# Output-K8 proxy + backend sampling replace it. Also drop any IU4/ngram
|
||||
# companions from the non-IU4 development lane.
|
||||
unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true
|
||||
MTP_DRAFT="$MODEL_DIR/$MTP_DRAFT_FILE"
|
||||
|
||||
# Plain dense model: no PromptForge .pfs sidecars, no Output-K8 proxy, no IU4
|
||||
# lane. The v3 MTP is driven by the standalone Q4_0 draft head through the
|
||||
# standard draft-mtp path. Unset any leftover PromptForge env lanes.
|
||||
unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
|
||||
unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
|
||||
unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
|
||||
unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
|
||||
unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
|
||||
|
||||
for f in "$MODEL" "$PROMPTFORGE_SIDECAR" "$PROMPTFORGE_GDN_SIDECAR" "$PROMPTFORGE_MTP_OUTPUT_K8_PROXY" "$MODEL_DIR/$MMPROJ_FILE"; do
|
||||
for f in "$MODEL" "$MTP_DRAFT" "$MODEL_DIR/$MMPROJ_FILE" "$CHAT_TEMPLATE_FILE"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "missing required file: $f" >&2
|
||||
exit 1
|
||||
@@ -95,6 +94,8 @@ export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_L
|
||||
exec "$LLAMA_BIN" \
|
||||
--model "$MODEL" \
|
||||
--mmproj "$MODEL_DIR/$MMPROJ_FILE" \
|
||||
--chat-template-file "$CHAT_TEMPLATE_FILE" \
|
||||
--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
|
||||
--alias "$ALIAS" \
|
||||
--host "$BIND_ADDR" \
|
||||
--port "$LISTEN_PORT" \
|
||||
@@ -113,6 +114,7 @@ exec "$LLAMA_BIN" \
|
||||
--metrics \
|
||||
--no-mmap \
|
||||
--spec-type draft-mtp \
|
||||
--model-draft "$MTP_DRAFT" \
|
||||
--spec-draft-device ROCm0 \
|
||||
--spec-draft-ngl 999 \
|
||||
--spec-draft-type-k f16 \
|
||||
@@ -121,10 +123,10 @@ 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 "$TEMPERATURE" \
|
||||
--top-k "$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