Skip to content

GitLab

Unverified Commit 5d043c16 authored by Kyle Sayers's avatar Kyle Sayers Committed by GitHub
Browse files

[Quant] Bamba SupportsQuant (#14698) 


Signed-off-by: default avatarKyle Sayers <kylesayrs@gmail.com>
parent 36d1ccb2
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/model_executor/models/bamba.py
View file @ 5d043c16
...@@ -33,7 +33,7 @@ from vllm.sequence import IntermediateTensors ...@@ -33,7 +33,7 @@ from vllm.sequence import IntermediateTensors
from vllm.utils import LayerBlockType from vllm.utils import LayerBlockType
from .interfaces import (HasInnerState, IsHybrid, SupportsLoRA, SupportsPP, from .interfaces import (HasInnerState, IsHybrid, SupportsLoRA, SupportsPP,
SupportsV0Only) SupportsQuant, SupportsV0Only)
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,
maybe_prefix) maybe_prefix)
...@@ -367,7 +367,7 @@ class BambaModel(nn.Module): ...@@ -367,7 +367,7 @@ class BambaModel(nn.Module):
class BambaForCausalLM(nn.Module, HasInnerState, SupportsLoRA, SupportsPP, class BambaForCausalLM(nn.Module, HasInnerState, SupportsLoRA, SupportsPP,
IsHybrid, SupportsV0Only): IsHybrid, SupportsV0Only, SupportsQuant):
packed_modules_mapping = { packed_modules_mapping = {
"qkv_proj": [ "qkv_proj": [
"q_proj", "q_proj",
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment