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

[Model] Enable BLOOM on V1 (#23488)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-24 21:30:47 +08:00
committed by GitHub
parent 416f05929a
commit e2db1164a1
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/bloom.py
View File

@@ -43,7 +43,7 @@ from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from .interfaces import SupportsPP, SupportsQuant, SupportsV0Only
from .interfaces import SupportsPP, SupportsQuant
from .utils import (AutoWeightsLoader, is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers,
maybe_prefix)
@@ -313,7 +313,7 @@ class BloomModel(nn.Module):
return loaded_params
class BloomForCausalLM(nn.Module, SupportsPP, SupportsV0Only, SupportsQuant):
class BloomForCausalLM(nn.Module, SupportsPP, SupportsQuant):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__()