Swap fleet naming + restore Qwen3.6-35B-A3B Q6_K_P on Dankserver
- Restore the pre-2026-08-17 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Q6_K_P + ngram-mod setup as frank-default-small on Dankserver (port 7770, upstream llama.cpp b10121, MoE experts on CPU via --n-cpu-moe 36). - Rename the CIRU Qwen3.8-27B ActiveFPX setup from frank-default-small to frank-default-large (Dankclaw, port 52625); bump to CTX_SIZE=262144 (native max) and PARALLEL=2 (96 GiB unified pool). - Retire the Qwen3.8-27B IQ4_XS FastMTP frank-default-large (Dankserver) to .AGENTTRASH. - deploy.sh: SERVICE[dankserver]=frank-default-small, SERVICE[dankclaw]=frank-default-large; HEALTH_WAIT[dankserver]=600.
This commit is contained in:
Frank
+7
-6
@@ -17,8 +17,8 @@
|
||||
# FRANK_SUDO_PW=... ./deploy.sh <target>
|
||||
#
|
||||
# Targets (2026-08-18 topology):
|
||||
# dankserver - llama.cpp FastMTP (frank-default-large.service, port 7770)
|
||||
# dankclaw - CIRU ROCmFPX llama.cpp (frank-default-small.service, port 52625)
|
||||
# dankserver - llama.cpp Qwen3.6-35B-A3B Q6_K_P (frank-default-small.service, port 7770)
|
||||
# dankclaw - CIRU ROCmFPX llama.cpp Qwen3.8-27B (frank-default-large.service, port 52625)
|
||||
set -euo pipefail
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -29,16 +29,17 @@ declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR SERVICE SERVICE_HEALTH DROP_CACHES
|
||||
REMOTE_USER[dankserver]=dank
|
||||
REMOTE_HOST[dankserver]=dankserver
|
||||
REMOTE_DIR[dankserver]="/home/dank/vLLM"
|
||||
SERVICE[dankserver]="frank-default-large"
|
||||
SERVICE[dankserver]="frank-default-small"
|
||||
SERVICE_HEALTH[dankserver]="http://127.0.0.1:7770/health"
|
||||
DROP_CACHES[dankserver]=0
|
||||
# Cold load: --no-mmap reads 15.7 GB through RAM; allow 10 minutes.
|
||||
HEALTH_WAIT[dankserver]=300
|
||||
# Cold load: --no-mmap reads the 30.6 GB Q6_K_P through RAM (MoE experts on
|
||||
# CPU); allow 20 minutes.
|
||||
HEALTH_WAIT[dankserver]=600
|
||||
|
||||
REMOTE_USER[dankclaw]=dank
|
||||
REMOTE_HOST[dankclaw]=dankclaw
|
||||
REMOTE_DIR[dankclaw]="/home/dank/vllmScripts"
|
||||
SERVICE[dankclaw]="frank-default-small"
|
||||
SERVICE[dankclaw]="frank-default-large"
|
||||
SERVICE_HEALTH[dankclaw]="http://127.0.0.1:52625/health"
|
||||
DROP_CACHES[dankclaw]=0
|
||||
# CIRU llama.cpp (ROCm 7.15) loads the 34.9 GiB ActiveFPX payload + MTP
|
||||
|
||||
@@ -1,62 +1,72 @@
|
||||
# Tunables for frank-default-large (llama.cpp, dankserver, RTX 3090).
|
||||
# Tunables for frank-default-large (CIRU llama.cpp, dankclaw, Strix Halo
|
||||
# gfx1151).
|
||||
#
|
||||
# Runtime: patched llama-server (HauhauCS FastMTP build) serving
|
||||
# HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF IQ4_XS with
|
||||
# the FastMTP 32K draft sidecar and the ngram-mod fallback. Single machine,
|
||||
# no pipeline split. Alias frank-default-large, port 7770.
|
||||
# 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).
|
||||
# This box is NVIDIA/CUDA, but the rule still applies to keep the env files
|
||||
# portable.
|
||||
# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
|
||||
|
||||
# Model files (downloaded to this directory from the HF repo).
|
||||
MODEL_DIR=/home/dank/models/hauhaucs-qwen38
|
||||
MODEL_FILE=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf
|
||||
DRAFT_FILE=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-FastMTP-32K.gguf
|
||||
# Patched llama.cpp binary. The FastMTP sidecar needs the patch; see AGENTS.md.
|
||||
# REQUIRED build flags: -DGGML_CUDA_FA=ON -DGGML_CUDA_FA_ALL_QUANTS=ON.
|
||||
# Without FA_ALL_QUANTS the q8_0 KV + flash attention fall back to a slow
|
||||
# path and prefill collapses ~12x (95 t/s vs 1300+ t/s at 8K prompt,
|
||||
# measured 2026-08-17). Do not rebuild without it.
|
||||
LLAMA_BIN=/home/dank/llama.cpp-fastmtp/build/bin/llama-server
|
||||
# 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=7770
|
||||
LISTEN_PORT=52625
|
||||
|
||||
# Context, single slot. 131072 (128K) leaves ~1.4 GiB VRAM headroom on the
|
||||
# 3090 with IQ4_XS + FastMTP + K q8_0 / V f16 KV. Lower to 122880 (120K) for
|
||||
# ~1.8 GiB headroom. KV per token = 16 attention layers x 4 KV heads x 256
|
||||
# dim: K q8_0 (1088 B/token) + V f16 (2048 B/token) = 3136 B/token/layer.
|
||||
CTX_SIZE=131072
|
||||
PARALLEL=1
|
||||
|
||||
# Speculative decoding. FastMTP (MTP depth 2) with the ngram-mod fallback.
|
||||
SPEC_DEFAULT=1
|
||||
MTP=1
|
||||
SPEC_DRAFT_N_MAX=2
|
||||
SPEC_DRAFT_NGL=all
|
||||
SPEC_DRAFT_P_MIN=0
|
||||
SPEC_NGRAM_MOD_N_MIN=48
|
||||
SPEC_NGRAM_MOD_N_MAX=64
|
||||
SPEC_NGRAM_MOD_N_MATCH=24
|
||||
|
||||
# KV quantization on GPU: K q8_0 + V f16 (user request: K=8, V=16).
|
||||
CACHE_TYPE_K=q8_0
|
||||
CACHE_TYPE_V=f16
|
||||
|
||||
# Batch sizing (user request).
|
||||
# Serving: 256K context (native max, n_ctx_train = 262144), 2 slots, f16 KV,
|
||||
# context checkpoints, prompt cache. Native MTP depth-4. The Strix Halo is
|
||||
# unified memory; the addressable pool is 96 GiB (VRAM is a pointer). KV at
|
||||
# 262144 x 2 slots is ~32 GiB (64 KiB/cell, 16 full-attn layers); total
|
||||
# sits well inside the 96 GiB pool.
|
||||
CTX_SIZE=262144
|
||||
PARALLEL=2
|
||||
BATCH_SIZE=2048
|
||||
UBATCH_SIZE=1024
|
||||
UBATCH_SIZE=2048
|
||||
CACHE_TYPE_K=f16
|
||||
CACHE_TYPE_V=f16
|
||||
CTX_CHECKPOINTS=32
|
||||
CACHE_RAM=8192
|
||||
|
||||
# Sampling - Qwen3.8 thinking-mode defaults.
|
||||
TEMPERATURE=1.0
|
||||
TOP_K=20
|
||||
# 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
|
||||
MIN_P=0.0
|
||||
|
||||
THREADS=8
|
||||
THREADS_HTTP=1
|
||||
# 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
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[Unit]
|
||||
Description=llama.cpp Qwen3.8-27B Aggressive IQ4_XS + FastMTP (dankserver, frank-default-large)
|
||||
Description=CIRU llama.cpp Qwen3.8-27B ActiveFPX PromptForge MTP (dankclaw, frank-default-large)
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
@@ -7,8 +7,8 @@ Wants=network-online.target
|
||||
Type=simple
|
||||
User=dank
|
||||
Group=dank
|
||||
Environment="FRANK_LARGE_ENV_FILE=/home/dank/vLLM/scripts/frank-default-large.env"
|
||||
ExecStart=/home/dank/vLLM/scripts/serve-frank-large.sh
|
||||
Environment="FRANK_LARGE_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-large.env"
|
||||
ExecStart=/home/dank/vllmScripts/scripts/serve-frank-large.sh
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
|
||||
@@ -1,71 +1,61 @@
|
||||
# Tunables for frank-default-small (CIRU llama.cpp, dankclaw, Strix Halo
|
||||
# gfx1151).
|
||||
# Tunables for frank-default-small (HauhauCS Qwen3.6-35B-A3B Q6_K_P,
|
||||
# ngram-mod spec, Dankserver, RTX 3090).
|
||||
#
|
||||
# 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-small, port 52625.
|
||||
# Runtime: upstream llama.cpp llama-server (b10121). RTX 3090 24 GB;
|
||||
# Ryzen 7 7700X; 62 GB RAM. MoE experts offloaded to CPU (--n-cpu-moe 36).
|
||||
# Restored 2026-08-18 (was the pre-2026-08-17-redo frank-default-small).
|
||||
#
|
||||
# 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.
|
||||
# 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 box is NVIDIA/CUDA, but the rule keeps the env portable.
|
||||
|
||||
# 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
|
||||
# Model files (already on disk; Q6_K_P GGUF + f16 mmproj vision encoder).
|
||||
MODEL_DIR=/home/dank/models
|
||||
MODEL_FILE=Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf
|
||||
MMPROJ_FILE=mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf
|
||||
# Upstream llama.cpp binary (b10121).
|
||||
LLAMA_SERVER=/home/dank/llama.cpp/build/bin/llama-server
|
||||
|
||||
ALIAS=frank-default-small
|
||||
BIND_ADDR=0.0.0.0
|
||||
LISTEN_PORT=52625
|
||||
LISTEN_PORT=7770
|
||||
|
||||
# Serving: 128K context (user request, 2026-08-18; model card default is
|
||||
# 64K), single slot, f16 KV, context checkpoints, prompt cache. Native MTP
|
||||
# depth-4. KV at 128K is 8 GiB (64 KiB/token); estimated total ~43 GiB of
|
||||
# the 64 GiB SVM pool, leaving ~21 GiB headroom.
|
||||
CTX_SIZE=131072
|
||||
PARALLEL=1
|
||||
BATCH_SIZE=2048
|
||||
UBATCH_SIZE=2048
|
||||
# 4 parallel slots x ~175104 ctx each = ~700000 total context pool.
|
||||
# Dual-f16 KV at 700000 cells leaves ~2.3 GiB free on the 3090.
|
||||
CTX_SIZE=700000
|
||||
PARALLEL=4
|
||||
|
||||
# Spec: ngram-mod (n_min=48, n_max=64, n_match=24).
|
||||
SPEC_TYPE=ngram-mod
|
||||
NGRAM_MOD_N_MIN=48
|
||||
NGRAM_MOD_N_MAX=64
|
||||
NGRAM_MOD_N_MATCH=24
|
||||
|
||||
# Expert offload: 36 of 40 layers keep MoE weights on CPU; 4 on GPU.
|
||||
N_CPU_MOE=36
|
||||
N_GPU_LAYERS=all
|
||||
|
||||
# KV cache on GPU, both K and V at f16.
|
||||
CACHE_TYPE_K=f16
|
||||
CACHE_TYPE_V=f16
|
||||
CTX_CHECKPOINTS=32
|
||||
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
|
||||
# Store SWA/context checkpoints in RAM to hold peak GPU memory down.
|
||||
CTX_CHECKPOINTS=4
|
||||
|
||||
# Big prefill batches (ubatch 3072 is the top prefill tier).
|
||||
BATCH_SIZE=8192
|
||||
UBATCH_SIZE=3072
|
||||
|
||||
# Eager RAM load (MoE experts on CPU; ~31 GB RAM).
|
||||
NO_MMAP=1
|
||||
|
||||
# Sampling (HauhauCS Qwen3.6-35B-A3B model card, thinking-general).
|
||||
TEMPERATURE=1.0
|
||||
TOP_K=20
|
||||
TOP_P=0.95
|
||||
MIN_P=0.0
|
||||
|
||||
# Compute threads lowered to 7 so other processes keep a core.
|
||||
THREADS=7
|
||||
THREADS_HTTP=8
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[Unit]
|
||||
Description=CIRU llama.cpp Qwen3.8-27B ActiveFPX PromptForge ngram MTP (dankclaw, frank-default-small)
|
||||
Description=llama.cpp Qwen3.6-35B-A3B Q6_K_P + ngram-mod (dankserver, frank-default-small)
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
@@ -7,8 +7,8 @@ Wants=network-online.target
|
||||
Type=simple
|
||||
User=dank
|
||||
Group=dank
|
||||
Environment="FRANK_SMALL_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-small.env"
|
||||
ExecStart=/home/dank/vllmScripts/scripts/serve-frank-small.sh
|
||||
Environment="FRANK_SMALL_ENV_FILE=/home/dank/vLLM/scripts/frank-default-small.env"
|
||||
ExecStart=/home/dank/vLLM/scripts/serve-frank-small.sh
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
|
||||
@@ -1,14 +1,16 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve the Qwen3.8-27B HauhauCS Aggressive IQ4_XS on Dankserver (RTX 3090).
|
||||
# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge as frank-default-large
|
||||
# via the CIRU ROCmFPX llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
|
||||
#
|
||||
# Runs a patched llama-server (HauhauCS FastMTP build, commit 4df29be +
|
||||
# HauhauCS-FastMTP-llama.cpp.patch) with the FastMTP draft sidecar and the
|
||||
# ngram-mod fallback. There is no pipeline split: the whole model lives on
|
||||
# the 3090.
|
||||
# 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 FastMTP draft sidecar requires the patched executable. Loading the
|
||||
# draft with the stock binary fails with "expected 5120, 248320, got 5120,
|
||||
# 32768" (see the HauhauCS repo README).
|
||||
# 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.
|
||||
@@ -24,44 +26,52 @@ if [[ -f "$ENV_FILE" ]]; then
|
||||
fi
|
||||
|
||||
# --- defaults (used when the env file does not set them) -------------------
|
||||
: "${MODEL_DIR:=/home/dank/models/hauhaucs-qwen38}"
|
||||
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf}"
|
||||
: "${DRAFT_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-FastMTP-32K.gguf}"
|
||||
: "${LLAMA_BIN:=/home/dank/llama.cpp-fastmtp/build/bin/llama-server}"
|
||||
: "${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:=7770}"
|
||||
: "${CTX_SIZE:=131072}"
|
||||
: "${PARALLEL:=1}"
|
||||
: "${SPEC_DEFAULT:=1}"
|
||||
: "${MTP:=1}"
|
||||
: "${SPEC_DRAFT_N_MAX:=2}"
|
||||
: "${SPEC_DRAFT_NGL:=all}"
|
||||
: "${SPEC_DRAFT_P_MIN:=0}"
|
||||
: "${SPEC_NGRAM_MOD_N_MIN:=48}"
|
||||
: "${SPEC_NGRAM_MOD_N_MAX:=64}"
|
||||
: "${SPEC_NGRAM_MOD_N_MATCH:=24}"
|
||||
: "${CACHE_TYPE_K:=q8_0}"
|
||||
: "${CACHE_TYPE_V:=f16}"
|
||||
: "${LISTEN_PORT:=52625}"
|
||||
: "${CTX_SIZE:=262144}"
|
||||
: "${PARALLEL:=2}"
|
||||
: "${BATCH_SIZE:=2048}"
|
||||
: "${UBATCH_SIZE:=1024}"
|
||||
: "${TEMPERATURE:=1.0}"
|
||||
: "${TOP_K:=20}"
|
||||
: "${UBATCH_SIZE:=2048}"
|
||||
: "${CACHE_TYPE_K:=f16}"
|
||||
: "${CACHE_TYPE_V:=f16}"
|
||||
: "${CTX_CHECKPOINTS:=32}"
|
||||
: "${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}"
|
||||
: "${MIN_P:=0.0}"
|
||||
: "${THREADS:=8}"
|
||||
: "${THREADS_HTTP:=1}"
|
||||
: "${REASONING:=on}"
|
||||
: "${REASONING_FORMAT:=deepseek}"
|
||||
: "${VERBOSITY:=4}"
|
||||
|
||||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||||
DRAFT="$MODEL_DIR/$DRAFT_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: $MODEL" >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -f "$DRAFT" ]]; then
|
||||
echo "missing draft file: $DRAFT" >&2
|
||||
if [[ ! -f "$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
|
||||
@@ -69,40 +79,41 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# --- speculative decoding: FastMTP (MTP) first, then ngram-mod fallback ----
|
||||
SPEC_ARGS=()
|
||||
SPEC_ARGS+=(--spec-type draft-mtp)
|
||||
SPEC_ARGS+=(--spec-draft-model "$DRAFT")
|
||||
SPEC_ARGS+=(--spec-draft-n-max "$SPEC_DRAFT_N_MAX")
|
||||
SPEC_ARGS+=(--spec-draft-ngl "$SPEC_DRAFT_NGL")
|
||||
SPEC_ARGS+=(--spec-draft-p-min "$SPEC_DRAFT_P_MIN")
|
||||
if [[ "$SPEC_DEFAULT" == "1" ]]; then
|
||||
SPEC_ARGS+=(--spec-default)
|
||||
SPEC_ARGS+=(--spec-ngram-mod-n-min "$SPEC_NGRAM_MOD_N_MIN")
|
||||
SPEC_ARGS+=(--spec-ngram-mod-n-max "$SPEC_NGRAM_MOD_N_MAX")
|
||||
SPEC_ARGS+=(--spec-ngram-mod-n-match "$SPEC_NGRAM_MOD_N_MATCH")
|
||||
fi
|
||||
# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
|
||||
export ROCM_PATH="$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 "$MODEL" \
|
||||
"${SPEC_ARGS[@]}" \
|
||||
--gpu-layers all \
|
||||
--no-mmap \
|
||||
--flash-attn on \
|
||||
--ctx-size "$CTX_SIZE" \
|
||||
--parallel "$PARALLEL" \
|
||||
--cache-type-k "$CACHE_TYPE_K" \
|
||||
--cache-type-v "$CACHE_TYPE_V" \
|
||||
--batch-size "$BATCH_SIZE" \
|
||||
--ubatch-size "$UBATCH_SIZE" \
|
||||
--temp "$TEMPERATURE" \
|
||||
--top-k "$TOP_K" \
|
||||
--top-p "$TOP_P" \
|
||||
--min-p "$MIN_P" \
|
||||
--threads "$THREADS" \
|
||||
--threads-http "$THREADS_HTTP" \
|
||||
--jinja \
|
||||
--alias "$ALIAS" \
|
||||
-lv "$VERBOSITY" \
|
||||
--host "$BIND_ADDR" \
|
||||
--port "$LISTEN_PORT"
|
||||
--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 "$CACHE_RAM" \
|
||||
--cache-prompt \
|
||||
--metrics \
|
||||
--spec-type draft-mtp \
|
||||
--spec-draft-device ROCm0 \
|
||||
--spec-draft-ngl 999 \
|
||||
--spec-draft-type-k f16 \
|
||||
--spec-draft-type-v f16 \
|
||||
--spec-draft-n-max "$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"
|
||||
|
||||
@@ -1,19 +1,13 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge via the CIRU ROCmFPX
|
||||
# llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
|
||||
# Serve HauhauCS Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive:Q6_K_P with
|
||||
# ngram-mod speculative decoding on Dankserver (RTX 3090, MoE experts on CPU).
|
||||
#
|
||||
# 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 llama-server (b10121). The model is a 35B-total /
|
||||
# 3B-active MoE vision-language model; --n-cpu-moe keeps most expert weights on
|
||||
# CPU so the non-expert tensors + KV cache fit the 24 GB 3090.
|
||||
#
|
||||
# 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-small.env in this directory unless
|
||||
# FRANK_SMALL_ENV_FILE overrides that path.
|
||||
# Tunables come from frank-default-small.env in this directory unless the
|
||||
# FRANK_SMALL_ENV_FILE environment variable overrides that path.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
@@ -25,95 +19,75 @@ if [[ -f "$ENV_FILE" ]]; then
|
||||
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}"
|
||||
# --- defaults (used when the env file does not set them) -----------------
|
||||
: "${MODEL_DIR:=/home/dank/models}"
|
||||
: "${MODEL_FILE:=Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf}"
|
||||
: "${MMPROJ_FILE:=mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf}"
|
||||
: "${LLAMA_SERVER:=/home/dank/llama.cpp/build/bin/llama-server}"
|
||||
: "${ALIAS:=frank-default-small}"
|
||||
: "${BIND_ADDR:=0.0.0.0}"
|
||||
: "${LISTEN_PORT:=52625}"
|
||||
: "${CTX_SIZE:=131072}"
|
||||
: "${PARALLEL:=1}"
|
||||
: "${BATCH_SIZE:=2048}"
|
||||
: "${UBATCH_SIZE:=2048}"
|
||||
: "${LISTEN_PORT:=7770}"
|
||||
: "${CTX_SIZE:=700000}"
|
||||
: "${PARALLEL:=4}"
|
||||
: "${SPEC_TYPE:=ngram-mod}"
|
||||
: "${NGRAM_MOD_N_MIN:=48}"
|
||||
: "${NGRAM_MOD_N_MAX:=64}"
|
||||
: "${NGRAM_MOD_N_MATCH:=24}"
|
||||
: "${CACHE_TYPE_K:=f16}"
|
||||
: "${CACHE_TYPE_V:=f16}"
|
||||
: "${CTX_CHECKPOINTS:=32}"
|
||||
: "${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}"
|
||||
: "${VERBOSITY:=4}"
|
||||
: "${N_CPU_MOE:=36}"
|
||||
: "${N_GPU_LAYERS:=all}"
|
||||
: "${BATCH_SIZE:=8192}"
|
||||
: "${UBATCH_SIZE:=3072}"
|
||||
: "${CTX_CHECKPOINTS:=4}"
|
||||
: "${NO_MMAP:=1}"
|
||||
: "${TEMPERATURE:=1.0}"
|
||||
: "${TOP_K:=20}"
|
||||
: "${TOP_P:=0.95}"
|
||||
: "${MIN_P:=0.0}"
|
||||
: "${THREADS:=7}"
|
||||
: "${THREADS_HTTP:=8}"
|
||||
|
||||
MODEL="$MODEL_DIR/$MODEL_FILE"
|
||||
export PROMPTFORGE_SIDECAR="$MODEL_DIR/$FFN_PFS"
|
||||
export PROMPTFORGE_GDN_SIDECAR="$MODEL_DIR/$GDN_PFS"
|
||||
export PROMPTFORGE_MODE="m2048_fused_tail1476"
|
||||
export GGML_CUDA_GRAPH_OPT=0
|
||||
export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1
|
||||
MMPROJ="$MODEL_DIR/$MMPROJ_FILE"
|
||||
|
||||
if [[ ! -f "$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: $PROMPTFORGE_GDN_SIDECAR" >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -x "$LLAMA_BIN" ]]; then
|
||||
echo "missing llama-server binary: $LLAMA_BIN" >&2
|
||||
for f in "$MODEL" "$MMPROJ"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "missing required file: $f" >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
if [[ ! -x "$LLAMA_SERVER" ]]; then
|
||||
echo "missing llama-server binary: $LLAMA_SERVER" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
|
||||
export ROCM_PATH="$ROCM_DEVEL"
|
||||
export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
|
||||
|
||||
exec "$LLAMA_BIN" \
|
||||
exec "$LLAMA_SERVER" \
|
||||
--model "$MODEL" \
|
||||
--mmproj "$MMPROJ" \
|
||||
--jinja \
|
||||
--spec-type "$SPEC_TYPE" \
|
||||
--spec-ngram-mod-n-min "$NGRAM_MOD_N_MIN" \
|
||||
--spec-ngram-mod-n-max "$NGRAM_MOD_N_MAX" \
|
||||
--spec-ngram-mod-n-match "$NGRAM_MOD_N_MATCH" \
|
||||
--cache-type-k "$CACHE_TYPE_K" \
|
||||
--cache-type-v "$CACHE_TYPE_V" \
|
||||
--verbosity "$VERBOSITY" \
|
||||
--ctx-size "$CTX_SIZE" \
|
||||
--parallel "$PARALLEL" \
|
||||
--n-cpu-moe "$N_CPU_MOE" \
|
||||
--gpu-layers "$N_GPU_LAYERS" \
|
||||
--batch-size "$BATCH_SIZE" \
|
||||
--ubatch-size "$UBATCH_SIZE" \
|
||||
--ctx-checkpoints "$CTX_CHECKPOINTS" \
|
||||
$([ "$NO_MMAP" = "1" ] && printf -- "--no-mmap") \
|
||||
--temp "$TEMPERATURE" \
|
||||
--top-k "$TOP_K" \
|
||||
--top-p "$TOP_P" \
|
||||
--min-p "$MIN_P" \
|
||||
--threads "$THREADS" \
|
||||
--threads-http "$THREADS_HTTP" \
|
||||
--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 "$CACHE_RAM" \
|
||||
--cache-prompt \
|
||||
--metrics \
|
||||
--spec-type draft-mtp \
|
||||
--spec-draft-device ROCm0 \
|
||||
--spec-draft-ngl 999 \
|
||||
--spec-draft-type-k f16 \
|
||||
--spec-draft-type-v f16 \
|
||||
--spec-draft-n-max "$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"
|
||||
--port "$LISTEN_PORT"
|
||||
|
||||
Reference in New Issue
Block a user