xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 13:06:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Quant] Arctic SupportsQuant (#13366)

Browse Source
This commit is contained in:
Kyle Sayers 2025-02-18 00:35:09 -05:00 committed by GitHub
parent 88787bce1d
commit 00294e1bc6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/arctic.py
View File

@ -33,7 +33,7 @@ from vllm.model_executor.utils import set_weight_attrs
from vllm.sequence import IntermediateTensors
from vllm.transformers_utils.configs.arctic import ArcticConfig
from .interfaces import SupportsPP
from .interfaces import SupportsPP, SupportsQuant
from .utils import (extract_layer_index, is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers,
maybe_prefix)
@ -423,7 +423,8 @@ class ArcticModel(nn.Module):
return hidden_states
class ArcticForCausalLM(nn.Module, SupportsPP):
class ArcticForCausalLM(nn.Module, SupportsPP, SupportsQuant):
packed_modules_mapping = {"qkv_proj": ["q_proj", "k_proj", "v_proj"]}
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__()