[Quant] BaiChuan SupportsQuant (vllm-project#13710)

ywang96 · Feb 23, 2025 · d5ca211 · d5ca211
1 parent 2c5e637
commit d5ca211
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/vllm/model_executor/models/baichuan.py b/vllm/model_executor/models/baichuan.py
@@ -46,7 +46,7 @@
 from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors
 
-from .interfaces import SupportsLoRA, SupportsPP
+from .interfaces import SupportsLoRA, SupportsPP, SupportsQuant
 from .utils import (is_pp_missing_parameter,
                     make_empty_intermediate_tensors_factory, make_layers)
 
@@ -334,7 +334,8 @@ def forward(
         return hidden_states
 
 
-class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
+class BaiChuanBaseForCausalLM(nn.Module, SupportsLoRA, SupportsPP,
+                              SupportsQuant):
     packed_modules_mapping = {
         "W_pack": ["W_pack"],
         "gate_up_proj": [