add SupportsQuant

Signed-off-by: Kyle Sayers <[email protected]>

Author: kylesayrs

vllm/model_executor/models/bloom.py

@@ -42,7 +42,7 @@
 from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors
 
-from .interfaces import SupportsPP, SupportsV0Only
+from .interfaces import SupportsPP, SupportsQuant, SupportsV0Only
 from .utils import (is_pp_missing_parameter,
                     make_empty_intermediate_tensors_factory, make_layers,
                     maybe_prefix)
@@ -279,7 +279,7 @@ def forward(
         return hidden_states
 
 
-class BloomForCausalLM(nn.Module, SupportsPP, SupportsV0Only):
+class BloomForCausalLM(nn.Module, SupportsPP, SupportsV0Only, SupportsQuant):
 
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super().__init__()