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

[SupportsQuant] Chameleon, Chatglm, Commandr (#15952)

Browse Source 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
This commit is contained in:
Kyle Sayers
2025-04-03 11:25:22 -04:00
committed by GitHub
parent 421c462948
commit 82e7e19a6e
3 changed files with 17 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -49,7 +49,7 @@ from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.sequence import IntermediateTensors
from .interfaces import SupportsLoRA, SupportsPP
from .interfaces import SupportsLoRA, SupportsPP, SupportsQuant
from .utils import (extract_layer_index, is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers,
maybe_prefix)
@@ -332,7 +332,7 @@ class CohereModel(nn.Module):
return hidden_states
class CohereForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
class CohereForCausalLM(nn.Module, SupportsLoRA, SupportsPP, SupportsQuant):
packed_modules_mapping = {
"qkv_proj": [
"q_proj",