feat(qwen3.5-122b): replace mistral-small-4 as gen (abliterated NVFP4, text-only)

bjk110/Qwen3.5-122B-A10B-abliterated-NVFP4 on ana-ml2 GPU 0 (heretic downed):
- stacks/qwen3.5-122b/ — vLLM serve via the repo's text-only patch (Qwen3.5 MoE is a
  multimodal arch but this checkpoint is text-only weights), --reasoning-parser qwen3,
  GPU 0 pin, :8013; entrypoint+patch mounted from the model dir.
- serve-qwen3.5-122b.yaml — displace heretic + serve + verify.
- litellm: REMOVED dead mistral-small-4 / -reasoning; added qwen3.5-122-a10b[-reasoning]
  + aliases qwen-large[-reasoning] + repointed gen[-reasoning] -> qwen (thinking split via
  chat_template_kwargs.enable_thinking + --reasoning-parser qwen3).

Verified live: qwen healthy on :8013; gen / qwen-large / qwen3.5-122-a10b route, and
gen-reasoning returns reasoning_content; mistral-small-4 removed.
NOTE: Worldtree character backend (was bound to mistral-small-4) is dark until repointed
(operator-acknowledged).
This commit is contained in:
2026-06-19 00:49:04 -07:00
parent 67102b5b94
commit 89c83c4271
4 changed files with 229 additions and 31 deletions
+72
View File
@@ -0,0 +1,72 @@
# Displace mistral-small-4 (heretic) on ana-ml2 GPU 0 and serve
# bjk110/Qwen3.5-122B-A10B-abliterated-NVFP4 (text-only) as the new `gen` model
# (operator 2026-06-19). Weights pre-staged at /tank/aimodels/qwen3.5-122b-a10b-nvfp4
# (incl. the repo's serving/entrypoint.sh + vllm_patches/ that the compose mounts).
#
# ⚠️ Downing mistral-small-4 takes down the Worldtree CHARACTER backend (vision-intact)
# until it's repointed — operator-acknowledged. REVERT = down qwen, up -d the heretic.
#
# scripts/elway ana-ml2 --playbook playbooks/serve-qwen3.5-122b.yaml
vars:
compose_dir: /opt/docker/compose/qwen3.5-122b
heretic_dir: /opt/docker/compose/mistral-small-4-heretic
model_dir: /tank/aimodels/qwen3.5-122b-a10b-nvfp4
host_port: "8013"
steps:
- name: Verify NVFP4 weights + the repo's patch/entrypoint are staged
shell: |
test -f {{ model_dir }}/model.safetensors.index.json \
&& test -f {{ model_dir }}/serving/entrypoint.sh \
&& test -f {{ model_dir }}/vllm_patches/patch_qwen35_moe_text.py
changed_when: "false"
- name: Ensure vLLM compile-cache dir exists (writable)
shell: mkdir -p {{ model_dir }}/.cache/vllm
creates: "{{ model_dir }}/.cache/vllm"
- name: Ensure compose dir exists
shell: mkdir -p {{ compose_dir }}
creates: "{{ compose_dir }}"
- name: Upload compose.yaml
upload:
src: stacks/qwen3.5-122b/compose.yaml
dest: "{{ compose_dir }}/compose.yaml"
mode: "0644"
- name: Seed .env from template (only if absent)
upload:
src: stacks/qwen3.5-122b/.env.example
dest: "{{ compose_dir }}/.env"
mode: "0644"
when: "[ ! -f {{ compose_dir }}/.env ]"
- name: Displace — down mistral-small-4-heretic (frees GPU 0; no-op if down)
shell: cd {{ heretic_dir }} && docker compose down
- name: Bring up qwen3.5-122b
shell: cd {{ compose_dir }} && docker compose up -d
- name: Wait for vLLM /health (allow ~15 min for patch + NVFP4 MoE load + warmup)
shell: |
for i in $(seq 1 180); do
curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
sleep 5
done
exit 1
changed_when: "false"
verify:
- name: /health returns 200
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
changed_when: "false"
- name: served model id is qwen3.5-122-a10b
shell: curl -sf http://localhost:{{ host_port }}/v1/models | grep -q qwen3.5-122-a10b
changed_when: "false"
- name: container running
shell: docker inspect vllm-qwen35-122b --format '{{.State.Status}}' | grep -q running
changed_when: "false"
+53 -31
View File
@@ -78,51 +78,73 @@ model_list:
model_info:
mode: chat
# --- Mistral Small 4 (official NVFP4) — creative-writing / general text. 119B
# MoE (6.5B active), vLLM on ana-ml2 GPU 0 (dedicated 96 GB Blackwell), :8010.
# Explicit entry shadows the "*" wildcard. TEXT-ONLY for now — vLLM 0.23.0's
# Mistral multimodal processor crashes at startup (loaded with image/video
# limit 0); vision returns when vLLM patches it. Deployed 2026-06-15. ---
- model_name: mistral-small-4
# --- Qwen3.5-122B-A10B (abliterated NVFP4, text-only) — the general / `gen` model.
# REPLACED mistral-small-4 on ana-ml2 GPU 0 (operator 2026-06-19; heretic downed,
# mistral entries REMOVED). bjk110 NVFP4 served on :8013 via vLLM + the text-only
# patch, served-name qwen3.5-122-a10b. Thinking split = chat_template_kwargs.
# enable_thinking + --reasoning-parser qwen3 (mirrors qwen3.6-35b-a3b). One upstream
# fanned out under qwen3.5-122-a10b[-reasoning] + aliases qwen-large[-reasoning] +
# gen[-reasoning]; the -reasoning variants enable thinking. Keep api_base in sync.
# ⚠️ Worldtree CHARACTER backend (was bound to mistral-small-4) is dark until
# repointed — operator-acknowledged. ---
- model_name: qwen3.5-122-a10b
litellm_params:
model: hosted_vllm/mistral-small-4
api_base: http://10.250.50.54:8010/v1
api_key: os.environ/VLLM_API_KEY
model_info:
mode: chat
# mistral-small-4-reasoning: same upstream checkpoint, reasoning ON (2026-06-15,
# operator wanted "medium" — but Mistral's reasoning_effort is BINARY, only
# 'none' or 'high' (a medium/low request 400s). 'high' is the sole reasoning-ON
# level, so it carries the -reasoning intent. LiteLLM forwards extra_body to
# vLLM; the mistral reasoning-parser splits [THINK]…[/THINK] into reasoning_content.
- model_name: mistral-small-4-reasoning
litellm_params:
model: hosted_vllm/mistral-small-4
api_base: http://10.250.50.54:8010/v1
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
reasoning_effort: high
chat_template_kwargs:
enable_thinking: false
model_info:
mode: chat
- model_name: qwen3.5-122-a10b-reasoning
litellm_params:
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
chat_template_kwargs:
enable_thinking: true
model_info:
mode: chat
- model_name: qwen-large
litellm_params:
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
chat_template_kwargs:
enable_thinking: false
model_info:
mode: chat
- model_name: qwen-large-reasoning
litellm_params:
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
chat_template_kwargs:
enable_thinking: true
model_info:
mode: chat
# aliases: gen -> mistral-small-4, gen-reasoning -> mistral-small-4-reasoning
# (operator 2026-06-19). Duplicate-entry aliases — keep api_base in sync with the
# two mistral-small-4 entries above.
- model_name: gen
litellm_params:
model: hosted_vllm/mistral-small-4
api_base: http://10.250.50.54:8010/v1
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
chat_template_kwargs:
enable_thinking: false
model_info:
mode: chat
- model_name: gen-reasoning
litellm_params:
model: hosted_vllm/mistral-small-4
api_base: http://10.250.50.54:8010/v1
model: hosted_vllm/qwen3.5-122-a10b
api_base: http://10.250.50.54:8013/v1
api_key: os.environ/VLLM_API_KEY
extra_body:
reasoning_effort: high
chat_template_kwargs:
enable_thinking: true
model_info:
mode: chat
+23
View File
@@ -0,0 +1,23 @@
# qwen3.5-122b (bjk110/Qwen3.5-122B-A10B-abliterated-NVFP4, text-only) — ana-ml2
# GPU 0 tunables. Real .env lives at /opt/docker/compose/qwen3.5-122b/.env.
# vllm/vllm-openai:latest per the repo (the text-only patch targets latest).
# MUTABLE tag — pin a digest once a known-good version is established.
QWEN35_IMAGE=vllm/vllm-openai:latest
QWEN35_CONTAINER_NAME=vllm-qwen35-122b
# Own port (8010=mistral heretic [downed], 8007=qwen36, 8011=selene — 8013 free).
QWEN35_PORT=8013
QWEN35_GPU_ID=0
# vLLM served-model-name; litellm fans out qwen3.5-122-a10b[-reasoning] + aliases
# (qwen-large, gen) onto this, differentiated by chat_template_kwargs.enable_thinking.
QWEN35_SERVED_NAME=qwen3.5-122-a10b
QWEN35_MAX_MODEL_LEN=131072
QWEN35_MAX_NUM_SEQS=4
QWEN35_GPU_MEM_UTIL=0.90
QWEN35_MAX_NUM_BATCHED_TOKENS=32768
# Optional upstream vLLM API key (empty = no auth; internal net only).
API_KEY=
+81
View File
@@ -0,0 +1,81 @@
# qwen3.5-122b — bjk110/Qwen3.5-122B-A10B-abliterated-NVFP4 on ana-ml2 GPU 0,
# REPLACING mistral-small-4 (operator 2026-06-19: down the heretic, serve this as
# the new general/`gen` model). Abliterated Qwen3.5 MoE (256 experts, 10B active),
# NVFP4 (compressed-tensors), HF format.
#
# SERVING (per the repo's serving/): Qwen3.5 MoE is a MULTIMODAL arch but this
# checkpoint is text-only, so vLLM needs the repo's text-only PATCH applied before
# startup. We reuse the repo's entrypoint.sh (applies the patch, then runs vLLM) and
# vllm_patches/, mounted from the downloaded model dir — keeps patch+checkpoint
# version-coupled. Thinking split via litellm extra_body chat_template_kwargs
# (enable_thinking) + --reasoning-parser qwen3 (mirrors the qwen3.6-35b-a3b pattern).
#
# DISPLACEMENT: GPU 0 fits one mistral-class model; bring this up only after downing
# mistral-small-4-heretic. REVERT = down this, `up -d` the heretic stack.
#
# NOTE: image is vllm/vllm-openai:latest per the repo (the patch targets latest) —
# MUTABLE tag; pin a digest once a known-good version is established.
#
# Tunables in .env.
name: qwen3.5-122b
services:
vllm-qwen35-122b:
image: ${QWEN35_IMAGE:-vllm/vllm-openai:latest}
container_name: ${QWEN35_CONTAINER_NAME:-vllm-qwen35-122b}
restart: unless-stopped
ipc: host
ports:
- "${QWEN35_PORT:-8013}:8000"
environment:
- ROLE=head
- TP_SIZE=1
- MODEL_CONTAINER_PATH=/models/qwen
- SERVED_MODEL_NAME=${QWEN35_SERVED_NAME:-qwen3.5-122-a10b}
- HOST_PORT=8000
- MAX_MODEL_LEN=${QWEN35_MAX_MODEL_LEN:-131072}
- MAX_NUM_SEQS=${QWEN35_MAX_NUM_SEQS:-4}
- GPU_MEMORY_UTILIZATION=${QWEN35_GPU_MEM_UTIL:-0.90}
- MAX_NUM_BATCHED_TOKENS=${QWEN35_MAX_NUM_BATCHED_TOKENS:-32768}
# --reasoning-parser qwen3 surfaces <think>…</think> as reasoning_content;
# the thinking on/off itself is per-request (litellm chat_template_kwargs).
- VLLM_EXTRA_ARGS=--reasoning-parser qwen3 --enable-chunked-prefill
- NVIDIA_VISIBLE_DEVICES=0
- PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
- VLLM_API_KEY=${API_KEY:-}
volumes:
# checkpoint + the repo's entrypoint/patch (downloaded with the model).
- /tank/aimodels/qwen3.5-122b-a10b-nvfp4:/models/qwen:ro
- /tank/aimodels/qwen3.5-122b-a10b-nvfp4/serving/entrypoint.sh:/entrypoint.sh:ro
- /tank/aimodels/qwen3.5-122b-a10b-nvfp4/vllm_patches:/patches:ro
- /tank/aimodels/qwen3.5-122b-a10b-nvfp4/.cache/vllm:/root/.cache/vllm
entrypoint: ["bash", "/entrypoint.sh"]
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids:
- "${QWEN35_GPU_ID:-0}"
capabilities:
- gpu
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 900s
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.name=Qwen3.5-122B-A10B (abliterated NVFP4)
- homepage.icon=mdi-creation
- homepage.description=Abliterated Qwen3.5 122B-A10B NVFP4, the new `gen` model (ana-ml2 GPU 0)
- homepage.href=http://10.250.50.54:${QWEN35_PORT:-8013}/docs
networks:
tnet:
name: traefik-net
external: true