Added VLLM Offline Serve working code.

README.md

@@ -104,6 +104,82 @@ vllm serve openai/gpt-oss-20b
 
 [Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)
 
+Offline Serve Code:
+- run this code after installing proper libraries as described, while additionally installing this:
+- `uv pip install openai-harmony`
+```python
+# source .oss/bin/activate
+
+import os
+os.environ["VLLM_USE_FLASHINFER_SAMPLER"] = "0"
+
+import json
+from openai_harmony import (
+    HarmonyEncodingName,
+    load_harmony_encoding,
+    Conversation,
+    Message,
+    Role,
+    SystemContent,
+    DeveloperContent,
+)
+ 
+from vllm import LLM, SamplingParams
+import os
+
+# --- 1) Render the prefill with Harmony ---
+encoding = load_harmony_encoding(HarmonyEncodingName.HARMONY_GPT_OSS)
+ 
+convo = Conversation.from_messages(
+    [
+        Message.from_role_and_content(Role.SYSTEM, SystemContent.new()),
+        Message.from_role_and_content(
+            Role.DEVELOPER,
+            DeveloperContent.new().with_instructions("Always respond in riddles"),
+        ),
+        Message.from_role_and_content(Role.USER, "What is the weather like in SF?"),
+    ]
+)
+ 
+prefill_ids = encoding.render_conversation_for_completion(convo, Role.ASSISTANT)
+ 
+# Harmony stop tokens (pass to sampler so they won't be included in output)
+stop_token_ids = encoding.stop_tokens_for_assistant_actions()
+ 
+# --- 2) Run vLLM with prefill ---
+llm = LLM(
+    model="openai/gpt-oss-20b",
+    trust_remote_code=True,
+    gpu_memory_utilization = 0.95,
+    max_num_batched_tokens=4096,
+    max_model_len=5000,
+    tensor_parallel_size=1
+)
+ 
+sampling = SamplingParams(
+    max_tokens=128,
+    temperature=1,
+    stop_token_ids=stop_token_ids,
+)
+ 
+outputs = llm.generate(
+    prompt_token_ids=[prefill_ids],   # batch of size 1
+    sampling_params=sampling,
+)
+ 
+# vLLM gives you both text and token IDs
+gen = outputs[0].outputs[0]
+text = gen.text
+output_tokens = gen.token_ids  # <-- these are the completion token IDs (no prefill)
+ 
+# --- 3) Parse the completion token IDs back into structured Harmony messages ---
+entries = encoding.parse_messages_from_completion_tokens(output_tokens, Role.ASSISTANT)
+ 
+# 'entries' is a sequence of structured conversation entries (assistant messages, tool calls, etc.).
+for message in entries:
+    print(f"{json.dumps(message.to_dict())}")
+```
+
 ## PyTorch / Triton
 
 To learn about how to use this model with PyTorch and Triton, check out our [reference implementations in the gpt-oss repository](https://github.com/openai/gpt-oss?tab=readme-ov-file#reference-pytorch-implementation).