Add vLLM v0.18.1 source tree with KV transfer abort fix

third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:

  vllm/v1/core/sched/scheduler.py:
    Replace fatal assert with graceful skip when KV transfer callback
    arrives for an already-aborted request during PD disaggregated serving.

Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

third_party/vllm/pyproject.toml

@@ -0,0 +1,174 @@
+[build-system]
+# Should be mirrored in requirements/build.txt
+requires = [
+    "cmake>=3.26.1",
+    "ninja",
+    "packaging>=24.2",
+    "setuptools>=77.0.3,<81.0.0",
+    "setuptools-scm>=8.0",
+    "torch == 2.10.0",
+    "wheel",
+    "jinja2",
+]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vllm"
+authors = [{name = "vLLM Team"}]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+readme = "README.md"
+description = "A high-throughput and memory-efficient inference and serving engine for LLMs"
+classifiers = [
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+]
+requires-python = ">=3.10,<3.14"
+dynamic = [ "version", "dependencies", "optional-dependencies"]
+
+[project.urls]
+Homepage="https://github.com/vllm-project/vllm"
+Documentation="https://docs.vllm.ai/en/latest/"
+Slack="https://slack.vllm.ai/"
+
+[project.scripts]
+vllm = "vllm.entrypoints.cli.main:main"
+
+[project.entry-points."vllm.general_plugins"]
+lora_filesystem_resolver = "vllm.plugins.lora_resolvers.filesystem_resolver:register_filesystem_resolver"
+lora_hf_hub_resolver = "vllm.plugins.lora_resolvers.hf_hub_resolver:register_hf_hub_resolver"
+
+[tool.setuptools_scm]
+# no extra settings needed, presence enables setuptools-scm
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["vllm*"]
+
+[tool.ruff.lint.per-file-ignores]
+"vllm/third_party/**" = ["ALL"]
+"vllm/version.py" = ["F401"]
+"vllm/_version.py" = ["ALL"]
+
+[tool.ruff.lint]
+select = [
+    # pycodestyle
+    "E",
+    # Pyflakes
+    "F",
+    # pyupgrade
+    "UP",
+    # flake8-bugbear
+    "B",
+    # flake8-implicit-str-concat
+    "ISC",
+    # flake8-simplify
+    "SIM",
+    # isort
+    "I",
+    # flake8-logging-format
+    "G",
+]
+ignore = [
+    # star imports
+    "F405", "F403",
+    # lambda expression assignment
+    "E731",
+    # zip without `strict=`
+    "B905",
+    # Loop control variable not used within loop body
+    "B007",
+    # f-string format
+    "UP032",
+]
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.mypy]
+plugins = ['pydantic.mypy']
+ignore_missing_imports = true
+check_untyped_defs = true
+follow_imports = "silent"
+
+[tool.pytest.ini_options]
+markers = [
+    "slow_test",
+    "skip_global_cleanup",
+    "core_model: enable this model test in each PR instead of only nightly",
+    "hybrid_model: models that contain mamba layers (including pure SSM and hybrid architectures)",
+    "cpu_model: enable this model test in CPU tests",
+    "cpu_test: mark test as CPU-only test",
+    "split: run this test as part of a split",
+    "distributed: run this test only in distributed GPU tests",
+    "optional: optional tests that are automatically skipped, include --optional to run them",
+]
+
+[tool.ty.src]
+respect-ignore-files = true
+
+[tool.ty.environment]
+python = "./.venv"
+
+[tool.typos.files]
+# these files may be written in non english words
+extend-exclude = ["tests/models/fixtures/*", "tests/prompts/*", "tests/tokenizers_/*",
+    "benchmarks/sonnet.txt", "tests/lora/data/*", "examples/pooling/token_embed/*", "build/*",
+    "vllm/third_party/*", "vllm/entrypoints/serve/instrumentator/static/*", "tests/entrypoints/openai/test_transcription_validation.py",
+    "docs/governance/process.md", "tests/v1/engine/test_fast_incdec_prefix_err.py", ".git/*"]
+ignore-hidden = false
+
+[tool.typos.default]
+extend-ignore-identifiers-re = [".*[Uu][Ee][0-9][Mm][0-9].*"]
+
+[tool.typos.default.extend-identifiers]
+bbc5b7ede = "bbc5b7ede"
+NOOPs = "NOOPs"
+nin_shortcut = "nin_shortcut"
+cudaDevAttrMaxSharedMemoryPerBlockOptin = "cudaDevAttrMaxSharedMemoryPerBlockOptin"
+
+depthwise_seperable_out_channel = "depthwise_seperable_out_channel"
+pard_token = "pard_token"
+ptd_token_id = "ptd_token_id"
+ser_de = "ser_de"
+shared_memory_per_block_optin = "shared_memory_per_block_optin"
+FoPE = "FoPE"
+k_ot = "k_ot"
+view_seperator = "view_seperator"
+inverse_std_variences = "inverse_std_variences"
+
+[tool.typos.default.extend-words]
+iy = "iy"
+indx = "indx"
+# intel cpu features
+tme = "tme"
+dout = "dout"
+Pn = "Pn"
+arange = "arange"
+thw = "thw"
+subtile = "subtile"
+HSA = "HSA"
+setp = "setp"
+CPY = "CPY"
+thr = "thr"
+Thr = "Thr"
+PARD = "PARD"
+pard = "pard"
+AKS = "AKS"
+ba = "ba"
+fo = "fo"
+nd = "nd"
+eles = "eles"
+datas = "datas"
+ser = "ser"
+ure = "ure"
+
+[tool.uv]
+no-build-isolation-package = ["torch"]