request.py 2.85 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
# SPDX-License-Identifier: Apache-2.0
from __future__ import annotations

import dataclasses
import functools
import json
from concurrent.futures import Future
from concurrent.futures._base import TimeoutError
from typing import Optional, Union, cast

from vllm.sampling_params import SamplingParams
12
13
14
from vllm.v1.structured_output.backend_types import (StructuredOutputGrammar,
                                                     StructuredOutputKey,
                                                     StructuredOutputOptions)
15
16
17
18
19
20


@dataclasses.dataclass
class StructuredOutputRequest:

    sampling_params: SamplingParams
21
22
    _grammar: Optional[Union[Future[StructuredOutputGrammar],
                             StructuredOutputGrammar]] = None
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41

    def _check_grammar_completion(self) -> bool:
        # NOTE: We have to lazy import to gate circular imports
        from vllm.v1.request import RequestStatus

        if isinstance(self._grammar, Future):
            try:
                # We will check whether the future is ready within 100 us
                self._grammar = self._grammar.result(timeout=0.0001)
                self.status = RequestStatus.WAITING
            except TimeoutError:
                return False
        return True

    @property
    def is_grammar_ready(self) -> bool:
        return self._check_grammar_completion()

    @property
42
    def grammar(self) -> Optional[StructuredOutputGrammar]:
43
        completed = self._check_grammar_completion()
44
45
        return cast(Optional[StructuredOutputGrammar],
                    self._grammar) if completed else None
46
47

    @grammar.setter
48
49
50
51
    def grammar(
        self, grammar: Union[StructuredOutputGrammar,
                             Future[StructuredOutputGrammar]]
    ) -> None:
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        self._grammar = grammar

    @functools.cached_property
    def structured_output_key(self) -> StructuredOutputKey:
        params = self.sampling_params.guided_decoding
        assert params is not None, "params can't be None."
        if params.json is not None:
            if not isinstance(params.json, str):
                json_str = json.dumps(params.json)
            else:
                json_str = params.json
            return (StructuredOutputOptions.JSON, json_str)
        elif params.json_object:
            return (StructuredOutputOptions.JSON_OBJECT, "")
        elif params.regex is not None:
            return (StructuredOutputOptions.REGEX, params.regex)
        elif params.choice is not None:
            if not isinstance(params.choice, str):
                json_str = json.dumps(params.choice)
            else:
                json_str = params.choice
            return (StructuredOutputOptions.CHOICE, json_str)
        elif params.grammar is not None:
            return (StructuredOutputOptions.GRAMMAR, params.grammar)
        else:
            raise ValueError("No valid structured output parameter found")