frank-medium: swap ROCmFPX llama.cpp runtime for vllm-radiance MXFP4
Rootless Quadlet on dankserver serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (the radiance stack's designated alternate target; ships its fp8 MTP head, no rewrite step) with the DFlash2-FP8 drafter at SPEC=7 on the 2x R9700s (TP=2, host network, :7770, alias frank-medium unchanged). - dankserver/frank-medium/: quadlet unit, container entrypoint (fork of serve-mxfp4.sh's patch block at pinned clone commit 97353293), healthcheck - dispatcher retires the root llama.cpp unit, re-tags the registry image to the localhost alias, installs the quadlet, waits on /health - planner maps dankserver/frank-medium/* to frank-medium; scripts-era mappings removed - ROCmFPX-era env/serve/unit/download scripts staged in scripts/.AGENTTRASH with .rocmfpx suffix; seams updated (frank_medium_quadlet.bats new)
This commit is contained in:
Frank committed
1 parent
db29c4d227
commit
6b647c1558
13 files changed
+566
-47
No files matched your search
+86
@@ -0,0 +1,86 @@
|
||||
#!/usr/bin/env bash
|
||||
# Download the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT payload for
|
||||
# frank-medium from HuggingFace into
|
||||
# /home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT.
|
||||
#
|
||||
# Run on Dankserver (the box that serves it). The repo is public, so the
|
||||
# download works anonymously; a token in ~/.cache/huggingface/token is used
|
||||
# when present, which keeps the ~28 GB main file clear of the anonymous
|
||||
# rate limit at full speed.
|
||||
#
|
||||
# bash scripts/download-q8agent.sh
|
||||
# bash scripts/download-q8agent.sh --verify-only
|
||||
#
|
||||
# The script is resumable (curl -C -) and verifies every artifact's size
|
||||
# afterwards, so a truncated file fails loudly instead of load-crashing.
|
||||
set -euo pipefail
|
||||
|
||||
REPO="kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF"
|
||||
DIR="/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT"
|
||||
EXPECTED=(
|
||||
"Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf:28214425952"
|
||||
"mmproj-Qwen3.8-27B-BF16.gguf:931145888"
|
||||
"mtp-Qwen3.8-27B-Q4_0.gguf:1680271648"
|
||||
)
|
||||
# The model card's MTP prompt-cache fix ships in the same repo as a patch;
|
||||
# fetched for reference only. This fork's main already carries the
|
||||
# speculative boundary in the context checkpoint, so nothing applies it.
|
||||
EXTRA=(
|
||||
"patches/mtp-prompt-cache-fix.patch"
|
||||
)
|
||||
|
||||
cd -- "$(dirname -- "$0")/.."
|
||||
|
||||
main() {
|
||||
local mode="download"
|
||||
[[ "${1:-}" == "--verify-only" ]] && mode="verify"
|
||||
mkdir -p "$DIR"
|
||||
cd "$DIR"
|
||||
|
||||
local token="" auth=()
|
||||
if [[ -r "$HOME/.cache/huggingface/token" ]]; then
|
||||
token="$(cat "$HOME/.cache/huggingface/token")"
|
||||
auth=(-H "Authorization: Bearer $token")
|
||||
else
|
||||
echo "no HF token at $HOME/.cache/huggingface/token; downloading anonymously"
|
||||
fi
|
||||
|
||||
dl() {
|
||||
local f="$1"
|
||||
mkdir -p "$(dirname "$f")"
|
||||
curl -fsSL -C - -o "$f" --retry 10 --retry-delay 5 --retry-max-time 10800 \
|
||||
"${auth[@]}" \
|
||||
"https://huggingface.co/$REPO/resolve/main/$f"
|
||||
echo " done: $f ($(du -h "$f" | cut -f1))"
|
||||
}
|
||||
|
||||
if [[ "$mode" == "download" ]]; then
|
||||
echo "downloading $REPO into $DIR"
|
||||
for entry in "${EXPECTED[@]}"; do
|
||||
dl "${entry%%:*}"
|
||||
done
|
||||
for f in "${EXTRA[@]}"; do
|
||||
dl "$f"
|
||||
done
|
||||
fi
|
||||
|
||||
echo "verifying sizes"
|
||||
local ok=1 f want act
|
||||
for entry in "${EXPECTED[@]}"; do
|
||||
f="${entry%%:*}"; want="${entry##*:}"
|
||||
act="$(stat -c%s "$f" 2>/dev/null || echo 0)"
|
||||
if [[ "$act" -eq "$want" ]]; then
|
||||
echo " OK $f ($act bytes)"
|
||||
else
|
||||
echo " BAD $f ($act bytes, want $want)" >&2
|
||||
ok=0
|
||||
fi
|
||||
done
|
||||
if [[ -z "$token" ]]; then
|
||||
echo "note: no token was used; sizes above are the integrity check"
|
||||
fi
|
||||
[[ "$ok" -eq 1 ]] || exit 1
|
||||
echo "all files present and sized correctly"
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,138 @@
|
||||
# Tunables for frank-medium (kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF,
|
||||
# charlie12345/ROCmFPX llama.cpp, Dankserver, 2x AMD Radeon AI PRO R9700).
|
||||
#
|
||||
# Hardware (2026-09-15): the RTX 3090 left Dankserver and two Radeon AI PRO
|
||||
# R9700 cards (Navi 48, gfx1201, RDNA4, 32,624 MiB each, PCIe 5.0 x16) took
|
||||
# its place. The Raphael iGPU (gfx1036) is still enumerated by HIP as the
|
||||
# third device. There is no XGMI link between the two cards and they sit in
|
||||
# different IOMMU groups, so any cross-GPU traffic goes over PCIe.
|
||||
#
|
||||
# Runtime: charlie12345/ROCmFPX (llama.cpp fork, ROCmFPX quant family; the
|
||||
# Q8_0_ROCMFPX_AGENT tensor type exists nowhere else - stock llama.cpp cannot
|
||||
# load this GGUF). Built for gfx1201 with the fork's self-contained ROCm
|
||||
# 7.14 toolchain so the host's stale /opt/rocm-6.3.3 install is never used:
|
||||
#
|
||||
# cd /home/dank/GitPackages/charlie-ROCmFPX
|
||||
# env JOBS=8 ./scripts/build-rocmfp4-rocm714-local.sh
|
||||
#
|
||||
# gfx1201 must be the build target: a gfx1200 binary links, loads the model
|
||||
# and then segfaults on this card (fork's docs/BUILD-AMD-ARCHITECTURES.md).
|
||||
#
|
||||
# Model: kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT - Q8_0_ROCMFPX_AGENT
|
||||
# (ftype 115), 26.28 GiB, 8.39 bpw, arch qwen35 (MoE), quantized from a
|
||||
# 51.3 GiB BF16 source. The AGENT routing keeps 12 more attention-output
|
||||
# projections at full Q8_0 than the plain 8-bit build, which buys a higher
|
||||
# MTP draft acceptance (0.953 vs 0.911) and that is the whole point of this
|
||||
# checkpoint. Model card documents 131,072 context.
|
||||
#
|
||||
# Parallelism (--split-mode layer, operator call 2026-09-15 "pipeline
|
||||
# parallelism"): layers are distributed across the two cards in order and
|
||||
# activations hop PCIe at the boundary. Measured with llama-bench
|
||||
# (pp4096 / tg128 / same at depth 32768, f16 KV, fa on, 3 reps):
|
||||
#
|
||||
# single R9700 1160.9 / 19.42 (fits: 26.27 GiB weights, ~5 GiB left)
|
||||
# layer 2x 1991.2 / 18.76 859.1 / 17.64
|
||||
# tensor 2x 271.8 / 26.26 228.6 / 25.09
|
||||
#
|
||||
# Tensor parallel wins decode (+40 %) but collapses prefill 7x: this build
|
||||
# has no RCCL (llama.cpp logs "AllReduce init failed; falling back to
|
||||
# meta-backend butterfly"), so every layer pays a slow cross-card reduction.
|
||||
# Agentic traffic is prefill-heavy, so layer split wins the workload. Revisit
|
||||
# if the fork ships a working RCCL tensor path.
|
||||
#
|
||||
# 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.
|
||||
|
||||
# charlie12345/ROCmFPX llama-server (self-contained ROCm 7.14 build, RPATH
|
||||
# points at the bundled runtime libs; no LD_LIBRARY_PATH needed).
|
||||
LLAMA_BIN=/home/dank/GitPackages/charlie-ROCmFPX/build-rdna4-rocm714/bin/llama-server
|
||||
|
||||
# Model package, fetched with scripts/download-q8agent.sh:
|
||||
# Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf 26.28 GiB main weights
|
||||
# mtp-Qwen3.8-27B-Q4_0.gguf 1.68 GiB MTP draft head
|
||||
# mmproj-Qwen3.8-27B-BF16.gguf 0.93 GiB vision tower (unused)
|
||||
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT
|
||||
MODEL_FILE=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf
|
||||
DRAFT_MODEL_FILE=mtp-Qwen3.8-27B-Q4_0.gguf
|
||||
|
||||
# Alias + network. The port is the fleet's dankserver endpoint; the alias is
|
||||
# what clients ask for, and it replaces the retired `frank-small`.
|
||||
ALIAS=frank-medium
|
||||
BIND_ADDR=0.0.0.0
|
||||
LISTEN_PORT=7770
|
||||
|
||||
# Device placement. HIP_VISIBLE_DEVICES hides the iGPU (device 2) so nothing
|
||||
# can drift onto shared system RAM; DEVICES is what llama.cpp splits across.
|
||||
HIP_VISIBLE_DEVICES=0,1
|
||||
DEVICES=ROCm0,ROCm1
|
||||
SPLIT_MODE=layer
|
||||
|
||||
# TENSOR_SPLIT empty = layers distributed by free VRAM (equal here).
|
||||
TENSOR_SPLIT=
|
||||
|
||||
NGL=999
|
||||
# Auto-fit has no business resizing a context we set explicitly.
|
||||
FIT=off
|
||||
FLASH_ATTN=on
|
||||
|
||||
# 131,072 tokens, one slot (the model card's documented window; the GGUF
|
||||
# reports n_ctx_train 262144, untested by the model author). Layer split
|
||||
# keeps each layer's KV on the card that owns the layer, so the window is
|
||||
# bounded by per-card free memory: ~5.6 GiB of KV per card at 131072 f16.
|
||||
CTX_SIZE=131072
|
||||
PARALLEL=1
|
||||
|
||||
# 26.28 GiB of weights + MTP draft + KV cache leaves ~15 GiB per card at this
|
||||
# context, so the batch shape is chosen for prefill throughput, not memory.
|
||||
BATCH_SIZE=2048
|
||||
UBATCH_SIZE=512
|
||||
NUM_THREADS=8
|
||||
THREAD_BATCH=8
|
||||
|
||||
# f16 K/V: an agent checkpoint is the wrong place to spend KV precision.
|
||||
CACHE_TYPE_K=f16
|
||||
CACHE_TYPE_V=f16
|
||||
CTX_CHECKPOINTS=8
|
||||
CACHE_RAM=8192
|
||||
|
||||
# Sampling: the checkpoint's instruct table.
|
||||
TEMPERATURE=0.7
|
||||
TOP_P=0.8
|
||||
TOP_K=20
|
||||
MIN_P=0.0
|
||||
PRESENCE_PENALTY=1.5
|
||||
|
||||
# Reasoning on; DeepSeek format projects the trace into reasoning_content
|
||||
# instead of literal thinking tags in content.
|
||||
REASONING=on
|
||||
REASONING_FORMAT=deepseek
|
||||
REASONING_BUDGET=-1
|
||||
|
||||
# Chat template: empty = the template embedded in the GGUF. Point this at
|
||||
# /home/dank/serverAppConfigs/scripts/chat-template.jinja to force the repo's
|
||||
# Sharp agent template instead.
|
||||
CHAT_TEMPLATE_FILE=
|
||||
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'
|
||||
|
||||
# MTP speculative decoding. n_max 6 / p_min 0.6 is the fork's measured
|
||||
# sweet spot for a MTP head with high acceptance; p_min 0.0 drafts
|
||||
# low-probability tokens that get rejected and makes MTP a net loss.
|
||||
SPEC_TYPE=draft-mtp
|
||||
SPEC_DRAFT_N_MAX=6
|
||||
SPEC_DRAFT_N_MIN=0
|
||||
SPEC_DRAFT_P_MIN=0.6
|
||||
SPEC_DRAFT_P_SPLIT=0.10
|
||||
SPEC_DRAFT_NGL=999
|
||||
SPEC_DRAFT_TYPE_K=f16
|
||||
SPEC_DRAFT_TYPE_V=f16
|
||||
SPEC_DRAFT_POLL=1
|
||||
SPEC_DRAFT_POLL_BATCH=1
|
||||
# The draft head rides the card that holds the target model's LAST layers:
|
||||
# the MTP head consumes the final hidden state, so pinning it to ROCm1 keeps
|
||||
# the per-token hop off the wire. (Under the abandoned tensor split the
|
||||
# draft must also be pinned to exactly one device or the meta-device KV
|
||||
# allocation aborts: GGML_ASSERT(buffer) in ggml-backend.cpp, measured
|
||||
# 2026-09-15.)
|
||||
SPEC_DRAFT_DEVICE=ROCm1
|
||||
@@ -0,0 +1,16 @@
|
||||
[Unit]
|
||||
Description=charlie12345/ROCmFPX llama.cpp serving kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT qwen35 MoE (dankserver, frank-medium, 2x Radeon AI PRO R9700)
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=dank
|
||||
Group=dank
|
||||
Environment="FRANK_MEDIUM_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-medium.env"
|
||||
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-medium.sh
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
+215
@@ -0,0 +1,215 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF as frank-medium via
|
||||
# the charlie12345/ROCmFPX llama.cpp runtime on Dankserver
|
||||
# (2x AMD Radeon AI PRO R9700, Navi 48, gfx1201, 32 GB each).
|
||||
#
|
||||
# Runtime: charlie12345/ROCmFPX main (c49ebdb, 2026-08-22), built for
|
||||
# gfx1201 with the fork's self-contained ROCm toolchain:
|
||||
#
|
||||
# cd /home/dank/GitPackages/charlie-ROCmFPX
|
||||
# env JOBS=8 ./scripts/build-rocmfp4-rocm714-local.sh
|
||||
# -> build-rdna4-rocm714/bin/llama-server
|
||||
#
|
||||
# That script downloads the gfx120X-all TheRock ROCm 7.14 toolchain into
|
||||
# ~/.local/share/rocm-7.14.0a20260624, builds with
|
||||
# -DCMAKE_HIP_ARCHITECTURES="gfx1200;gfx1201", copies the ROCm runtime
|
||||
# (hip/hsa/rocblas/hipblaslt + their kernel libraries) next to the binary and
|
||||
# sets RPATH=$ORIGIN/../lib on it. The resulting service is self-contained:
|
||||
# no LD_LIBRARY_PATH, and the host's stale /opt/rocm-6.3.3 cannot leak in.
|
||||
# gfx1201 is NOT interchangeable with gfx1200 on this card (the fork's
|
||||
# docs/BUILD-AMD-ARCHITECTURES.md: a gfx1200 build links, loads and then
|
||||
# segfaults), and the build verifies the emitted code objects afterwards.
|
||||
#
|
||||
# Model: kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT (Q8_0_ROCMFPX_AGENT,
|
||||
# ftype 115, arch qwen35 MoE), 26.28 GiB main file, plus a separate
|
||||
# MTP draft head and an mmproj vision tower. 8.39 bpw; the AGENT routing
|
||||
# keeps 13 of the 17 attention-output projections at full Q8_0, which is
|
||||
# what makes the MTP draft land ~0.95 of its guesses. A stock llama.cpp
|
||||
# cannot load this GGUF at all - Q8_0_ROCMFPX exists only in this fork.
|
||||
#
|
||||
# Parallelism: --split-mode layer across both cards (operator call
|
||||
# 2026-09-15). Layers are distributed in order and activations hop PCIe at
|
||||
# the boundary; measured llama-bench: layer 1991/18.8 tok/s (pp4096/tg128)
|
||||
# vs tensor 272/26.3 and single-card 1161/19.4. Tensor wins decode +40 %
|
||||
# but its prefill collapses 7x on this build (no RCCL: "AllReduce init
|
||||
# failed; falling back to meta-backend butterfly"), so layer split wins the
|
||||
# prefill-heavy agentic workload.
|
||||
#
|
||||
# Tunables come from frank-medium.env unless FRANK_MEDIUM_ENV_FILE
|
||||
# overrides that path.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ENV_FILE="${FRANK_MEDIUM_ENV_FILE:-$SCRIPT_DIR/frank-medium.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) -----------------
|
||||
: "${LLAMA_BIN:=/home/dank/GitPackages/charlie-ROCmFPX/build-rdna4-rocm714/bin/llama-server}"
|
||||
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT}"
|
||||
: "${MODEL_FILE:=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf}"
|
||||
: "${DRAFT_MODEL_FILE:=mtp-Qwen3.8-27B-Q4_0.gguf}"
|
||||
: "${ALIAS:=frank-medium}"
|
||||
: "${BIND_ADDR:=0.0.0.0}"
|
||||
: "${LISTEN_PORT:=7770}"
|
||||
|
||||
# Devices: ROCm0/ROCm1 are the two R9700s; the Raphael iGPU enumerates as
|
||||
# ROCm2 (gfx1036) and is hidden from HIP so nothing can drift onto it.
|
||||
: "${HIP_VISIBLE_DEVICES:=0,1}"
|
||||
: "${DEVICES:=ROCm0,ROCm1}"
|
||||
: "${SPLIT_MODE:=tensor}"
|
||||
: "${TENSOR_SPLIT:=}"
|
||||
: "${NGL:=999}"
|
||||
: "${FIT:=off}"
|
||||
: "${FLASH_ATTN:=on}"
|
||||
|
||||
: "${CTX_SIZE:=131072}"
|
||||
: "${PARALLEL:=1}"
|
||||
: "${BATCH_SIZE:=2048}"
|
||||
: "${UBATCH_SIZE:=512}"
|
||||
: "${NUM_THREADS:=8}"
|
||||
: "${THREAD_BATCH:=8}"
|
||||
: "${CACHE_TYPE_K:=f16}"
|
||||
: "${CACHE_TYPE_V:=f16}"
|
||||
: "${CTX_CHECKPOINTS:=8}"
|
||||
: "${CACHE_RAM:=8192}"
|
||||
|
||||
# Sampling: the checkpoint's instruct table.
|
||||
: "${TEMPERATURE:=0.7}"
|
||||
: "${TOP_P:=0.8}"
|
||||
: "${TOP_K:=20}"
|
||||
: "${MIN_P:=0.0}"
|
||||
: "${PRESENCE_PENALTY:=1.5}"
|
||||
|
||||
# Reasoning: the model is an agent checkpoint; keep the trace and project it
|
||||
# into the API's reasoning_content field rather than literal thinking tags.
|
||||
: "${REASONING:=on}"
|
||||
: "${REASONING_FORMAT:=deepseek}"
|
||||
: "${REASONING_BUDGET:=-1}"
|
||||
|
||||
# Chat template: empty means "use the template embedded in the GGUF".
|
||||
: "${CHAT_TEMPLATE_FILE:=}"
|
||||
: "${CHAT_TEMPLATE_KWARGS:={\"enable_thinking\":true,\"preserve_thinking\":true}}"
|
||||
|
||||
# MTP draft head (separate GGUF, --spec-type draft-mtp). SPEC_DRAFT_DEVICE
|
||||
# must name exactly one device: under tensor mode an unsplit draft joins the
|
||||
# meta-device KV allocation and aborts while building the KV cache
|
||||
# (GGML_ASSERT(buffer) in ggml-backend.cpp, 2026-09-15).
|
||||
: "${SPEC_TYPE:=draft-mtp}"
|
||||
: "${SPEC_DRAFT_N_MAX:=6}"
|
||||
: "${SPEC_DRAFT_N_MIN:=0}"
|
||||
: "${SPEC_DRAFT_P_MIN:=0.6}"
|
||||
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
|
||||
: "${SPEC_DRAFT_NGL:=999}"
|
||||
: "${SPEC_DRAFT_DEVICE:=}"
|
||||
: "${SPEC_DRAFT_TYPE_K:=f16}"
|
||||
: "${SPEC_DRAFT_TYPE_V:=f16}"
|
||||
: "${SPEC_DRAFT_POLL:=1}"
|
||||
: "${SPEC_DRAFT_POLL_BATCH:=1}"
|
||||
|
||||
# Text only: the server must not try to autoload the vision tower. Vision
|
||||
# stays on frank-large (Dankclaw), which is where the fleet routes images.
|
||||
NO_MMPROJ="${NO_MMPROJ:-1}"
|
||||
|
||||
export HIP_VISIBLE_DEVICES
|
||||
|
||||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||||
if [[ ! -x "$LLAMA_BIN" ]]; then
|
||||
echo "missing executable runtime: $LLAMA_BIN" >&2
|
||||
echo "build it with: cd $(dirname "$(dirname "$LLAMA_BIN")")/.. && env JOBS=8 ./scripts/build-rocmfp4-rocm714-local.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -r "$MODEL" ]]; then
|
||||
echo "missing or unreadable required artifact: $MODEL" >&2
|
||||
echo "fetch it with: bash $SCRIPT_DIR/download-q8agent.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ -n "$CHAT_TEMPLATE_FILE" && ! -r "$CHAT_TEMPLATE_FILE" ]]; then
|
||||
echo "missing or unreadable chat template: $CHAT_TEMPLATE_FILE" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# --- speculative decoding (MTP draft head) --------------------------------
|
||||
SPEC_ARGS=()
|
||||
if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
|
||||
SPEC_ARGS=(
|
||||
--spec-type "$SPEC_TYPE"
|
||||
--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"
|
||||
)
|
||||
if [[ "$SPEC_TYPE" == *draft-mtp* ]]; then
|
||||
DRAFT_MODEL="$MODEL_DIR/$DRAFT_MODEL_FILE"
|
||||
if [[ ! -r "$DRAFT_MODEL" ]]; then
|
||||
echo "missing or unreadable draft model: $DRAFT_MODEL" >&2
|
||||
exit 1
|
||||
fi
|
||||
SPEC_ARGS+=(
|
||||
--spec-draft-model "$DRAFT_MODEL"
|
||||
--spec-draft-ngl "$SPEC_DRAFT_NGL"
|
||||
--spec-draft-type-k "$SPEC_DRAFT_TYPE_K"
|
||||
--spec-draft-type-v "$SPEC_DRAFT_TYPE_V"
|
||||
--spec-draft-poll "$SPEC_DRAFT_POLL"
|
||||
--spec-draft-poll-batch "$SPEC_DRAFT_POLL_BATCH"
|
||||
)
|
||||
if [[ -n "$SPEC_DRAFT_DEVICE" ]]; then
|
||||
SPEC_ARGS+=(--spec-draft-device "$SPEC_DRAFT_DEVICE")
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- template + placement -------------------------------------------------
|
||||
TEMPLATE_ARGS=()
|
||||
if [[ -n "$CHAT_TEMPLATE_FILE" ]]; then
|
||||
TEMPLATE_ARGS+=(--chat-template-file "$CHAT_TEMPLATE_FILE")
|
||||
TEMPLATE_ARGS+=(--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS")
|
||||
fi
|
||||
|
||||
PLACEMENT_ARGS=(--device "$DEVICES" --split-mode "$SPLIT_MODE")
|
||||
if [[ -n "$TENSOR_SPLIT" ]]; then
|
||||
PLACEMENT_ARGS+=(--tensor-split "$TENSOR_SPLIT")
|
||||
fi
|
||||
|
||||
MMPROJ_ARGS=()
|
||||
if [[ "$NO_MMPROJ" == "1" ]]; then
|
||||
MMPROJ_ARGS=(--no-mmproj)
|
||||
fi
|
||||
|
||||
exec "$LLAMA_BIN" \
|
||||
--model "$MODEL" \
|
||||
--alias "$ALIAS" \
|
||||
--host "$BIND_ADDR" \
|
||||
--port "$LISTEN_PORT" \
|
||||
--jinja \
|
||||
--gpu-layers "$NGL" \
|
||||
--fit "$FIT" \
|
||||
--parallel "$PARALLEL" \
|
||||
--ctx-size "$CTX_SIZE" \
|
||||
--batch-size "$BATCH_SIZE" \
|
||||
--ubatch-size "$UBATCH_SIZE" \
|
||||
--flash-attn "$FLASH_ATTN" \
|
||||
--cache-type-k "$CACHE_TYPE_K" \
|
||||
--cache-type-v "$CACHE_TYPE_V" \
|
||||
--threads "$NUM_THREADS" \
|
||||
--threads-batch "$THREAD_BATCH" \
|
||||
--ctx-checkpoints "$CTX_CHECKPOINTS" \
|
||||
--cache-ram "$CACHE_RAM" \
|
||||
--cache-prompt \
|
||||
--metrics \
|
||||
--temp "$TEMPERATURE" \
|
||||
--top-p "$TOP_P" \
|
||||
--top-k "$TOP_K" \
|
||||
--min-p "$MIN_P" \
|
||||
--presence-penalty "$PRESENCE_PENALTY" \
|
||||
--reasoning "$REASONING" \
|
||||
--reasoning-format "$REASONING_FORMAT" \
|
||||
--reasoning-budget "$REASONING_BUDGET" \
|
||||
"${TEMPLATE_ARGS[@]}" \
|
||||
"${PLACEMENT_ARGS[@]}" \
|
||||
"${MMPROJ_ARGS[@]}" \
|
||||
"${SPEC_ARGS[@]}"
|
||||
Reference in new issue
Block a user