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/examples/offline_inference/context_extension.py

@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""
+This script demonstrates how to extend the context length
+of a Qwen model using the YARN method (rope_parameters)
+and run a simple chat example.
+
+Usage:
+    python examples/offline_inference/context_extension.py
+"""
+
+from vllm import LLM, RequestOutput, SamplingParams
+
+
+def create_llm():
+    rope_theta = 1000000
+    original_max_position_embeddings = 32768
+    factor = 4.0
+
+    # Use yarn to extend context
+    hf_overrides = {
+        "rope_parameters": {
+            "rope_theta": rope_theta,
+            "rope_type": "yarn",
+            "factor": factor,
+            "original_max_position_embeddings": original_max_position_embeddings,
+        },
+        "max_model_len": int(original_max_position_embeddings * factor),
+    }
+
+    llm = LLM(model="Qwen/Qwen3-0.6B", hf_overrides=hf_overrides)
+    return llm
+
+
+def run_llm_chat(llm):
+    sampling_params = SamplingParams(
+        temperature=0.8,
+        top_p=0.95,
+        max_tokens=128,
+    )
+
+    conversation = [
+        {"role": "system", "content": "You are a helpful assistant"},
+        {"role": "user", "content": "Hello"},
+        {"role": "assistant", "content": "Hello! How can I assist you today?"},
+    ]
+    outputs = llm.chat(conversation, sampling_params, use_tqdm=False)
+    return outputs, [
+        conversation,
+    ]
+
+
+def print_outputs(outputs: list[RequestOutput], conversations: list):
+    print("\nGenerated Outputs:\n" + "-" * 80)
+    for i, output in enumerate(outputs):
+        prompt = conversations[i]
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}\n")
+        print(f"Generated text: {generated_text!r}")
+        print("-" * 80)
+
+
+def main():
+    llm = create_llm()
+    outputs, conversations = run_llm_chat(llm)
+    print_outputs(outputs, conversations)
+
+
+if __name__ == "__main__":
+    main()