Initial commit

Signed-off-by: MOVZX <movzx@yahoo.com>

.env.example

@@ -0,0 +1,55 @@
+# ── network ──────────────────────────────────────────────────────────────────
+HOST_BIND_ADDR=0.0.0.0
+HOST_PORT=8080
+VLLM_API_KEY=
+
+# ── model ────────────────────────────────────────────────────────────────────
+MODEL_DIR=/data/models/halt95/Swift1.5-Qwen3.8-Flash-Next-W4A16-Merlin
+MODEL_MOUNT_PATH=/models/Qwen3.8-Flash-Next
+MODEL_NAME=Hinata
+
+# ── image and container ──────────────────────────────────────────────────────
+IMAGE=qwen38-flash-next
+IMAGE_TAG=latest
+CONTAINER_NAME=vllm
+# CACHE_HOST_DIR=/srv/vllm-cache
+
+# ── engine ───────────────────────────────────────────────────────────────────
+# Card hosting the PLE offload home (no CUDA context there).
+PLE_HOME=0
+# GPU lane, in bus order. The shipped shape uses all four cards.
+CUDA_VISIBLE_DEVICES=0,1,2,3
+# Topology selector (opt-in): 0 keeps the fixed shipped settings | 1 | strict.
+# The image has no numactl, so AUTO_TOPO_BIND=1 is skipped.
+AUTO_TOPO=0
+AUTO_TOPO_NCCL=legacy
+AUTO_TOPO_BIND=0
+# LANE_GPUS=auto
+# LANE_CPUS=0-15,16-31
+TOPO_TIMEOUT=20
+# Bounds-guard telemetry: off | warn | fail.
+GUARD=warn
+# 1 adds the two logging-only counters (exact-restart counters /30 s, FP8 KV clips /300 s).
+COUNTERS=0
+# Seconds between engine stats lines (throughput, KV usage, queue depth).
+VLLM_LOG_STATS_INTERVAL=1
+
+# Extracted from orcarouter/Qwen3.8-Flash-Next-Uncensored, hidden 2560
+QWEN38_ABLITERATION=Qwen3.8-Flash-Next-Uncensored
+ABLITERATION_DIR=./abliteration
+
+# ── lifecycle, logs, health ──────────────────────────────────────────────────
+LOG_MAX_SIZE=100m
+LOG_MAX_FILE=14
+
+# The image healthcheck is a real one-token generation, not /v1/models. Only the tuning is here.
+HEALTHCHECK_INTERVAL=60s
+HEALTHCHECK_TIMEOUT=90s
+HEALTHCHECK_START_PERIOD=30m
+HEALTHCHECK_RETRIES=3
+
+# ── build (docker compose build reads these) ──────────────────────────────────────
+UV_CACHE_DIR=/root/.cache/uv
+PIP_CACHE_DIR=/root/.cache/pip
+MAX_JOBS=32
+ARCH=8.6