biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] Logits processors extensibility (#19912)

Browse Source 
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
Signed-off-by: Andrew Feldman <afeld2012@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
afeldman-nm
2025-08-16 15:59:17 -04:00
committed by GitHub
parent 4fc722eca4
commit bf7f470b22
22 changed files with 1312 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/v1/worker/test_gpu_input_batch.py
View File

@@ -13,7 +13,7 @@ from vllm.platforms import current_platform
from vllm.sampling_params import SamplingParams
from vllm.utils import is_pin_memory_available, make_tensor_with_pad
from vllm.v1.pool.metadata import PoolingMetadata
from vllm.v1.sample.logits_processor import LogitsProcessorManager
from vllm.v1.sample.logits_processor import LogitsProcessors
from vllm.v1.sample.metadata import SamplingMetadata
from vllm.v1.worker.block_table import BlockTable, MultiGroupBlockTable
from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
@@ -169,7 +169,7 @@ def _construct_expected_sampling_metadata(
and all(x == 1 for x in repetition_penalties)),
allowed_token_ids_mask=allowed_token_ids_mask,
bad_words_token_ids=bad_words_token_ids,
logitsprocs=LogitsProcessorManager(),
logitsprocs=LogitsProcessors(),
)