初始提交：天垓150兼容引擎 I0–I4/I6/I7

tests/fixtures/fake-model/config.json

@@ -0,0 +1,4 @@
+{
+  "model_type": "llama",
+  "architectures": ["LlamaForCausalLM"]
+}

tests/fixtures/fake-model/tokenizer.json

@@ -0,0 +1,3 @@
+{
+  "version": "1.0"
+}

tests/fixtures/fake-model/tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+  "tokenizer_class": "LlamaTokenizer"
+}

tests/test_contract.py

@@ -0,0 +1,96 @@
+import os
+import subprocess
+import unittest
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+
+
+class EngineContractTest(unittest.TestCase):
+    def test_locked_values_match(self) -> None:
+        example = (ROOT / "task_info.env.example").read_text(encoding="utf-8")
+        workflow_env = (ROOT / ".gitea/workflows/task_info.env").read_text(encoding="utf-8")
+        dockerfile = (ROOT / "Dockerfile").read_text(encoding="utf-8")
+        self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", example)
+        self.assertIn("GPU_TYPE=Iluvatar_bi-150", example)
+        self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", workflow_env)
+        self.assertIn("GPU_TYPE=Iluvatar_bi-150", workflow_env)
+        self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", dockerfile)
+        self.assertIn("GPU_TYPE=Iluvatar_bi-150", dockerfile)
+        self.assertIn(
+            "registry.iluvatar.com.cn:10443/customer/sz/vllm0.17.0-4.4.0-x86:v4.1",
+            dockerfile,
+        )
+        self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", example)
+        self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", workflow_env)
+        self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", dockerfile)
+
+    def test_ci_does_not_submit_platform_task(self) -> None:
+        workflow = (ROOT / ".gitea/workflows/build.yml").read_text(encoding="utf-8")
+        self.assertNotIn("adminApi", workflow)
+        self.assertNotIn("modelhub.org.cn", workflow)
+        self.assertIn("build-only", workflow)
+        self.assertIn('tags:', workflow)
+
+    def test_no_zip_or_contest_targets(self) -> None:
+        makefile = (ROOT / "Makefile").read_text(encoding="utf-8")
+        self.assertNotIn("package", makefile)
+        self.assertNotIn("submit", makefile)
+        self.assertFalse((ROOT / "contest").exists())
+        self.assertFalse((ROOT / "computility-run.yaml").exists())
+
+    def test_dry_run_prints_plan(self) -> None:
+        env = os.environ.copy()
+        env.pop("FRAMEWORK", None)
+        env.pop("GPU_TYPE", None)
+        env.pop("MODEL_DIR", None)
+        completed = subprocess.run(
+            ["bash", "scripts/entrypoint.sh", "--dry-run"],
+            cwd=ROOT,
+            env=env,
+            text=True,
+            capture_output=True,
+            check=False,
+        )
+        self.assertEqual(completed.returncode, 0, completed.stderr)
+        self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", completed.stdout)
+        self.assertIn("GPU_TYPE=Iluvatar_bi-150", completed.stdout)
+        self.assertIn("python3 -m vllm.entrypoints.openai.api_server", completed.stdout)
+        self.assertIn("dry-run: 不启动进程，不访问平台", completed.stdout)
+        self.assertNotIn("modelhub.org.cn", completed.stdout)
+        self.assertIn("<|user|>", completed.stdout)
+
+    def test_dry_run_rejects_forbidden_framework(self) -> None:
+        env = os.environ.copy()
+        env["FRAMEWORK"] = "vllm_fix_tokenizer"
+        completed = subprocess.run(
+            ["bash", "scripts/entrypoint.sh", "--dry-run"],
+            cwd=ROOT,
+            env=env,
+            text=True,
+            capture_output=True,
+            check=False,
+        )
+        self.assertNotEqual(completed.returncode, 0)
+        self.assertIn("vllm_fix_tokenizer", completed.stderr)
+
+    def test_tokenizer_patch_stays_off(self) -> None:
+        import shutil
+        import tempfile
+
+        import apply_patches
+
+        with tempfile.TemporaryDirectory() as tmp:
+            model = Path(tmp) / "model"
+            shutil.copytree(ROOT / "tests" / "fixtures" / "fake-model", model)
+            result = apply_patches.apply_all(
+                model,
+                (ROOT / "patches/chat_template/default_chat_template.jinja").read_text(encoding="utf-8"),
+                apply_patches.load_whitelist(ROOT / "patches/architectures/whitelist.txt"),
+                {},
+            )
+        self.assertFalse(result["tokenizer"]["applied"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_r2_chat_template.py

@@ -0,0 +1,67 @@
+import json
+import shutil
+import tempfile
+import unittest
+from pathlib import Path
+
+import apply_patches
+
+ROOT = Path(__file__).resolve().parents[1]
+FIXTURE = ROOT / "tests" / "fixtures" / "fake-model"
+TEMPLATE = (ROOT / "patches" / "chat_template" / "default_chat_template.jinja").read_text(encoding="utf-8")
+WHITELIST = apply_patches.load_whitelist(ROOT / "patches" / "architectures" / "whitelist.txt")
+ALIASES = apply_patches.load_aliases(ROOT / "patches" / "architectures" / "aliases.json")
+
+
+class ChatTemplateTest(unittest.TestCase):
+    def setUp(self) -> None:
+        self.tmp = tempfile.TemporaryDirectory()
+        self.model = Path(self.tmp.name) / "model"
+        shutil.copytree(FIXTURE, self.model)
+
+    def tearDown(self) -> None:
+        self.tmp.cleanup()
+
+    def test_injects_missing_template(self) -> None:
+        result = apply_patches.apply_chat_template(self.model, TEMPLATE)
+        self.assertTrue(result["injected"])
+        data = json.loads((self.model / "tokenizer_config.json").read_text(encoding="utf-8"))
+        self.assertEqual(data["chat_template"], TEMPLATE)
+
+    def test_keeps_existing_template(self) -> None:
+        path = self.model / "tokenizer_config.json"
+        data = json.loads(path.read_text(encoding="utf-8"))
+        data["chat_template"] = "already-set"
+        path.write_text(json.dumps(data), encoding="utf-8")
+        result = apply_patches.apply_chat_template(self.model, TEMPLATE)
+        self.assertFalse(result["injected"])
+        kept = json.loads(path.read_text(encoding="utf-8"))
+        self.assertEqual(kept["chat_template"], "already-set")
+
+    def test_force_overwrites_template(self) -> None:
+        path = self.model / "tokenizer_config.json"
+        data = json.loads(path.read_text(encoding="utf-8"))
+        data["chat_template"] = "already-set"
+        path.write_text(json.dumps(data), encoding="utf-8")
+        result = apply_patches.apply_chat_template(self.model, TEMPLATE, force=True)
+        self.assertTrue(result["injected"])
+
+    def test_missing_tokenizer_config_fails(self) -> None:
+        (self.model / "tokenizer_config.json").unlink()
+        with self.assertRaises(apply_patches.PatchError):
+            apply_patches.apply_chat_template(self.model, TEMPLATE)
+
+    def test_preview_renders_roles(self) -> None:
+        text = apply_patches.preview_default_template(
+            [
+                {"role": "system", "content": "你是助手"},
+                {"role": "user", "content": "你好"},
+            ]
+        )
+        self.assertIn("<|user|>\n你好<|end|>\n", text)
+        self.assertTrue(text.endswith("<|assistant|>\n"))
+        self.assertIn("message['role']", TEMPLATE)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_r4_architectures.py

@@ -0,0 +1,65 @@
+import json
+import shutil
+import tempfile
+import unittest
+from pathlib import Path
+
+import apply_patches
+
+ROOT = Path(__file__).resolve().parents[1]
+FIXTURE = ROOT / "tests" / "fixtures" / "fake-model"
+WHITELIST = apply_patches.load_whitelist(ROOT / "patches" / "architectures" / "whitelist.txt")
+
+
+class ArchitectureTest(unittest.TestCase):
+    def setUp(self) -> None:
+        self.tmp = tempfile.TemporaryDirectory()
+        self.model = Path(self.tmp.name) / "model"
+        shutil.copytree(FIXTURE, self.model)
+
+    def tearDown(self) -> None:
+        self.tmp.cleanup()
+
+    def write_architectures(self, names: list[str]) -> None:
+        path = self.model / "config.json"
+        data = json.loads(path.read_text(encoding="utf-8"))
+        data["architectures"] = names
+        path.write_text(json.dumps(data), encoding="utf-8")
+
+    def test_whitelist_passes(self) -> None:
+        result = apply_patches.apply_architectures(self.model, WHITELIST, {}, "fail")
+        self.assertEqual(result["architectures"], ["LlamaForCausalLM"])
+        self.assertFalse(result["changed"])
+
+    def test_unknown_architecture_fails(self) -> None:
+        self.write_architectures(["ExampleForCausalLM"])
+        with self.assertRaises(apply_patches.PatchError) as ctx:
+            apply_patches.apply_architectures(self.model, WHITELIST, {}, "fail")
+        self.assertIn("ExampleForCausalLM", str(ctx.exception))
+
+    def test_unknown_architecture_skip_keeps_name(self) -> None:
+        self.write_architectures(["ExampleForCausalLM"])
+        result = apply_patches.apply_architectures(self.model, WHITELIST, {}, "skip")
+        self.assertEqual(result["skipped"], ["ExampleForCausalLM"])
+        data = json.loads((self.model / "config.json").read_text(encoding="utf-8"))
+        self.assertEqual(data["architectures"], ["ExampleForCausalLM"])
+
+    def test_alias_rewrites_to_whitelist(self) -> None:
+        self.write_architectures(["LlamaForCausalLMAlias"])
+        result = apply_patches.apply_architectures(
+            self.model,
+            WHITELIST,
+            {"LlamaForCausalLMAlias": "LlamaForCausalLM"},
+            "fail",
+        )
+        self.assertEqual(result["rewritten"], ["LlamaForCausalLMAlias->LlamaForCausalLM"])
+        data = json.loads((self.model / "config.json").read_text(encoding="utf-8"))
+        self.assertEqual(data["architectures"], ["LlamaForCausalLM"])
+
+    def test_shipped_aliases_are_empty(self) -> None:
+        aliases = apply_patches.load_aliases(ROOT / "patches" / "architectures" / "aliases.json")
+        self.assertEqual(aliases, {})
+
+
+if __name__ == "__main__":
+    unittest.main()