[Model Runner V2] Support custom logits processors (#56497)

Signed-off-by: David Cheung <d7cheung@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
David Cheung
2026-09-19 17:46:49 +00:00
committed by GitHub
co-authored by Claude Nick Hill
parent 751f6807d9
commit 5302d1fe40
32 changed files with 1215 additions and 510 deletions
+38 -7
View File
@@ -1,6 +1,9 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Sequence
from types import SimpleNamespace
import numpy as np
import pytest
import torch
@@ -10,6 +13,10 @@ if not torch.cuda.is_available():
pytest.skip("CUDA required for sampler flag tests", allow_module_level=True)
from vllm.sampling_params import SamplingParams
from vllm.v1.worker.gpu.sample.logits_processor import (
LogitsContext,
LogitsProcessor,
)
from vllm.v1.worker.gpu.sample.sampler import Sampler
from vllm.v1.worker.gpu.states import RequestState
@@ -23,7 +30,7 @@ class MockReasoningConfig:
natural_reasoning_end_token_ids = [91]
def _make_sampler() -> Sampler:
def _make_sampler(custom_logits_processors: Sequence[LogitsProcessor] = ()) -> Sampler:
req_states = RequestState(
max_num_reqs=4,
max_model_len=64,
@@ -33,11 +40,12 @@ def _make_sampler() -> Sampler:
device=DEVICE,
)
return Sampler(
vllm_config=SimpleNamespace(reasoning_config=MockReasoningConfig()),
max_num_reqs=4,
vocab_size=VOCAB_SIZE,
device=DEVICE,
req_states=req_states,
reasoning_config=MockReasoningConfig(),
custom_logits_processors=custom_logits_processors,
)
@@ -65,23 +73,46 @@ def test_logits_processing_cache_matches_request_features(
sampling_params: SamplingParams, expected: bool
):
sampler = _make_sampler()
sampler.add_request(3, prompt_len=1, sampling_params=sampling_params)
sampler.add_request(3, sampling_params=sampling_params)
assert sampler.needs_logits_processing[3] == expected
def test_logits_processing_cache_is_overwritten_when_slot_is_reused():
sampler = _make_sampler()
sampler.add_request(3, 1, SamplingParams.for_sampler_warmup())
sampler.add_request(3, 1, SamplingParams())
sampler.add_request(3, SamplingParams.for_sampler_warmup())
sampler.add_request(3, SamplingParams())
assert not sampler.needs_logits_processing[3]
class _GateProcessor(LogitsProcessor):
"""Reports a fixed admission decision from add_request()."""
def __init__(self, admitted: bool):
self.admitted = admitted
def add_request(self, req_idx: int, sampling_params: SamplingParams) -> bool:
return self.admitted
def apply(self, logits: torch.Tensor, ctx: LogitsContext) -> torch.Tensor:
raise AssertionError("the pipeline never runs in this test")
@pytest.mark.parametrize("admitted", [True, False])
def test_custom_processor_add_request_gates_pipeline_flag(admitted: bool):
"""A custom processor's add_request() return value is OR-ed into the
per-request needs_logits_processing flag."""
sampler = _make_sampler(custom_logits_processors=[_GateProcessor(admitted)])
sampler.add_request(3, SamplingParams())
assert sampler.needs_logits_processing[3] == admitted
def test_logits_processing_cache_only_checks_active_requests():
sampler = _make_sampler()
sampler.add_request(0, 1, SamplingParams(temperature=0.0))
sampler.add_request(2, 1, SamplingParams.for_sampler_warmup())
sampler.add_request(0, SamplingParams(temperature=0.0))
sampler.add_request(2, SamplingParams.for_sampler_warmup())
sampling_only = np.array([0], dtype=np.int32)
with_processing = np.array([0, 2], dtype=np.int32)