xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-28 11:41:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Quant] BaiChuan SupportsQuant (#13710)

Browse Source
This commit is contained in:
Kyle Sayers 2025-02-22 22:21:15 -05:00 committed by GitHub
parent 2c5e637b57
commit d5ca2110f1
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/baichuan.py
View File

@ -46,7 +46,7 @@ from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.sampling_metadata import SamplingMetadata from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors from vllm.sequence import IntermediateTensors
from .interfaces import SupportsLoRA, SupportsPP from .interfaces import SupportsLoRA, SupportsPP, SupportsQuant
from .utils import (is_pp_missing_parameter, from .utils import (is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers) make_empty_intermediate_tensors_factory, make_layers)
@ -334,7 +334,8 @@ class BaiChuanModel(nn.Module):
return hidden_states return hidden_states
class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA, SupportsPP): class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA, SupportsPP,
SupportsQuant):
packed_modules_mapping = { packed_modules_mapping = {
"W_pack": ["W_pack"], "W_pack": ["W_pack"],
"gate_up_proj": [ "gate_up_proj": [