commit 391302289de5c0946cb1623561ac896be69d1638
Author: wanglin <2281216234@qq.com>
Date:   Sat Oct 3 18:29:26 2026 +0800

    enginex-bi100-compat v1: preflight 兼容增强引擎（R2/R3/R3b/R4/R7），结构与引擎修复模式同型，25 项自测全通过

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..99756a6
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+__pycache__/
+*.pyc
+/tmp/
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..9a43f22
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,44 @@
+# enginex-bi100-compat
+#
+# 天数智芯 天垓100（Iluvatar_bi-100）· 文本生成 · vLLM「兼容增强」引擎。
+#
+# 不动模型、不动卡，只把「引擎镜像层」的结构性不兼容在启动前修掉。
+# 结构与社区已上线引擎 EngineX-Sunrise/enginex-S2-vllm-fix-tokenizer 完全同型
+# （Dockerfile + entrypoint.sh + 修补脚本 + README），该模式已在曦望 S2 生产验证。
+#
+# 修什么（全部有日志实证，见 README.md）：
+#   R3  extra_special_tokens 是 list            -> transformers 崩（社区已上线修复，已合并）
+#   R3b tokenizer_class 是坏类名                -> 加载异常（社区已上线修复，已合并）
+#   R2  模型没有 chat_template                  -> /v1/chat/completions 400/空输出
+#   R4  architectures 是镜像未注册类名          -> KeyError / MODEL_NOT_SUPPORTED
+#   R7  镜像缺 ixformer.contrib.vllm.layers     -> ModuleNotFoundError（MoE）
+#
+# 为什么选 bi-100：本人 37 个验证失败里，bi-100 单卡 10 例为全平台最集中；
+# 且该卡社区通过率约 51%（15 张卡最低），修好收益最大。
+
+FROM git.modelhub.org.cn:9443/enginex-iluvatar/bi100-3.2.3-x86-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3
+
+LABEL org.opencontainers.image.title="enginex-bi100-compat" \
+      org.opencontainers.image.description="Iluvatar bi-100 vLLM text-generation engine with preflight compatibility patches (R2/R3/R3b/R4/R7)" \
+      com.modelhubxc.engine.target-card="Iluvatar_bi-100" \
+      com.modelhubxc.engine.framework="vllm" \
+      com.modelhubxc.engine.task-type="text-generation" \
+      com.modelhubxc.engine.baseline="EngineX-Iluvatar/enginex-vllm-bi100-qwen36" \
+      com.modelhubxc.engine.pattern="EngineX-Sunrise/enginex-S2-vllm-fix-tokenizer"
+
+# 修补脚本 + R7 纯 PyTorch shim（都只是小文本文件，无权重）
+COPY preflight.py /opt/
+COPY entrypoint.sh /opt/
+COPY detect_tokenizer.py /opt/
+COPY shims/ /opt/shims/
+
+RUN chmod +x /opt/entrypoint.sh /opt/preflight.py \
+    && python3 -c "import ast,io;[ast.parse(io.open(f,encoding='utf-8').read()) for f in ['/opt/preflight.py','/opt/detect_tokenizer.py','/opt/shims/ixformer/contrib/vllm/layers/__init__.py']]" \
+    && bash -n /opt/entrypoint.sh \
+    && echo "[enginex-bi100-compat] preflight syntax OK"
+
+# R7：让 shims 全局可 import（平台若覆盖 entrypoint 也仍然生效）
+ENV PYTHONPATH=/opt/shims:${PYTHONPATH}
+ENV MODEL_DIR=/model
+
+ENTRYPOINT ["/opt/entrypoint.sh"]
diff --git a/computility-run.yaml b/computility-run.yaml
new file mode 100644
index 0000000..e420255
--- /dev/null
+++ b/computility-run.yaml
@@ -0,0 +1,31 @@
+# enginex-bi100-compat 的启动配置
+#
+# 与平台 bi-100 × vllm × text-generation 的原生 build-config 逐项一致，
+# 只把 command 换成「先过 preflight 再 exec 原命令」：
+#     python3 /workspace/compat/serve.py -- <原 command...>
+#
+# 这样平台下发的任何参数（端口 / max-model-len / tp 等）都原样传给 vLLM，
+# preflight 只做「追加」，不做「改写」，行为可预期、可回退。
+concurrency: 1
+command:
+  - python3
+  - /workspace/compat/serve.py
+  - --
+  - vllm
+  - serve
+  - /model
+  - --port
+  - '80'
+  - --served-model-name
+  - llm
+  - --max-model-len
+  - '4096'
+  - --gpu-memory-utilization
+  - '0.9'
+  - --enforce-eager
+  - --trust-remote-code
+  - -tp
+  - '1'
+env:
+  - name: PYTHONPATH
+    value: /workspace/compat/shims:/workspace/compat
diff --git a/detect_tokenizer.py b/detect_tokenizer.py
new file mode 100644
index 0000000..ede8122
--- /dev/null
+++ b/detect_tokenizer.py
@@ -0,0 +1,36 @@
+import os
+import json
+
+
+def detect(model_dir):
+    """判定 tokenizer 类型：fast / sentencepiece / bpe / unknown
+
+    与社区已上线引擎 EngineX-Sunrise/enginex-S2-vllm-fix-tokenizer 的
+    detect_tokenizer.py 保持一致（同一判定口径，便于两套引擎交叉验证）。
+    """
+    cfg_path = os.path.join(model_dir, "tokenizer_config.json")
+    cls = ""
+    if os.path.exists(cfg_path):
+        try:
+            with open(cfg_path, encoding="utf-8") as f:
+                cls = (json.load(f) or {}).get("tokenizer_class", "") or ""
+        except Exception:  # noqa: BLE001
+            cls = ""
+    try:
+        files = set(os.listdir(model_dir))
+    except Exception:  # noqa: BLE001
+        files = set()
+
+    if "tokenizer.json" in files:
+        return "fast", cls
+    if "tokenizer.model" in files:
+        return "sentencepiece", cls
+    if "vocab.json" in files and "merges.txt" in files:
+        return "bpe", cls
+    return "unknown", cls
+
+
+if __name__ == "__main__":
+    import sys
+    t, c = detect(sys.argv[1] if len(sys.argv) > 1 else "/model")
+    print(t, c)
diff --git a/entrypoint.sh b/entrypoint.sh
new file mode 100644
index 0000000..3b670ee
--- /dev/null
+++ b/entrypoint.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# enginex-bi100-compat 入口：启动前修补 -> exec vllm serve
+#
+# 与社区已上线引擎 EngineX-Sunrise/enginex-S2-vllm-fix-tokenizer 同一模式
+# （detect -> fix -> `exec vllm serve "$MODEL_DIR" $EXTRA "$@"`），
+# 只是把「只修 tokenizer」升级成「修 tokenizer + chat_template + 架构 + 缺模块」。
+#
+# 平台会把 GPU 数、端口、max-model-len 等参数作为 "$@" 传进来，原样透传。
+set -u
+
+MODEL_DIR=${MODEL_DIR:-${1:-/model}}
+# 若第一个参数不是目录，则认为是平台传入的 vllm 参数，MODEL_DIR 仍用默认 /model
+if [ $# -gt 0 ] && [ -d "$1" ]; then
+    MODEL_DIR="$1"
+    shift
+fi
+
+FIX_LOG=/tmp/mhxc_preflight.json
+echo "[entrypoint] model dir: $MODEL_DIR"
+echo "[entrypoint] args: $*"
+
+EXTRA=""
+if python3 /opt/preflight.py --model "$MODEL_DIR" --out "$FIX_LOG" >/tmp/mhxc_preflight.out 2>/tmp/mhxc_preflight.err; then
+    # 从 JSON 里取 extra_args（用 python 解析，避免依赖 jq）
+    EXTRA=$(python3 - "$FIX_LOG" <<'PY'
+import json, sys, shlex
+try:
+    with open(sys.argv[1], encoding="utf-8") as f:
+        d = json.load(f)
+    print(" ".join(shlex.quote(a) for a in (d.get("extra_args") or [])))
+except Exception as e:
+    print("")
+PY
+)
+    echo "[entrypoint] preflight extra args: ${EXTRA:-（无）}"
+    sed 's/^/[entrypoint] preflight: /' /tmp/mhxc_preflight.err 2>/dev/null || true
+else
+    echo "[entrypoint] preflight 执行失败，按原命令继续（不阻断启动）"
+    sed 's/^/[entrypoint] preflight: /' /tmp/mhxc_preflight.err 2>/dev/null || true
+fi
+
+echo "[entrypoint] starting vllm..."
+# shellcheck disable=SC2086
+exec vllm serve "$MODEL_DIR" $EXTRA "$@"