Sync from v0.13

vllm/entrypoints/serve/disagg/protocol.py

@@ -0,0 +1,90 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from vllm.entrypoints.openai.protocol import (
+    ChatCompletionLogProbs,
+    Logprob,
+    SamplingParams,
+    StreamOptions,
+)
+from vllm.utils import random_uuid
+
+
+####### Tokens IN <> Tokens OUT #######
+class GenerateRequest(BaseModel):
+    request_id: str = Field(
+        default_factory=lambda: f"{random_uuid()}",
+        description=(
+            "The request_id related to this request. If the caller does "
+            "not set it, a random_uuid will be generated. This id is used "
+            "through out the inference process and return in response."
+        ),
+    )
+    token_ids: list[int]
+    """The token ids to generate text from."""
+
+    # features: MultiModalFeatureSpec
+    # TODO (NickLucche): implement once Renderer work is completed
+    features: str | None = None
+    """The processed MM inputs for the model."""
+
+    sampling_params: SamplingParams
+    """The sampling parameters for the model."""
+
+    model: str | None = None
+
+    stream: bool | None = False
+    stream_options: StreamOptions | None = None
+    cache_salt: str | None = Field(
+        default=None,
+        description=(
+            "If specified, the prefix cache will be salted with the provided "
+            "string to prevent an attacker to guess prompts in multi-user "
+            "environments. The salt should be random, protected from "
+            "access by 3rd parties, and long enough to be "
+            "unpredictable (e.g., 43 characters base64-encoded, corresponding "
+            "to 256 bit)."
+        ),
+    )
+    priority: int = Field(
+        default=0,
+        description=(
+            "The priority of the request (lower means earlier handling; "
+            "default: 0). Any priority other than 0 will raise an error "
+            "if the served model does not use priority scheduling."
+        ),
+    )
+    kv_transfer_params: dict[str, Any] | None = Field(
+        default=None,
+        description="KVTransfer parameters used for disaggregated serving.",
+    )
+
+
+class GenerateResponseChoice(BaseModel):
+    index: int
+    logprobs: ChatCompletionLogProbs | None = None
+    # per OpenAI spec this is the default
+    finish_reason: str | None = "stop"
+    token_ids: list[int] | None = None
+
+
+class GenerateResponse(BaseModel):
+    request_id: str = Field(
+        default_factory=lambda: f"{random_uuid()}",
+        description=(
+            "The request_id related to this request. If the caller does "
+            "not set it, a random_uuid will be generated. This id is used "
+            "through out the inference process and return in response."
+        ),
+    )
+    choices: list[GenerateResponseChoice]
+
+    prompt_logprobs: list[dict[int, Logprob] | None] | None = None
+
+    kv_transfer_params: dict[str, Any] | None = Field(
+        default=None,
+        description="KVTransfer parameters used for disaggregated serving.",
+    )