[Core] Pipeline Parallel Support (#4412)
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
This commit is contained in:
@@ -21,7 +21,7 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
|
||||
DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
|
||||
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
|
||||
from vllm.model_executor.sampling_metadata import SamplingMetadata
|
||||
from vllm.sequence import SamplerOutput
|
||||
from vllm.sequence import IntermediateTensors, SamplerOutput
|
||||
|
||||
|
||||
def load_column_parallel_weight(param: torch.nn.Parameter,
|
||||
@@ -412,6 +412,7 @@ class Phi3SmallForCausalLM(nn.Module):
|
||||
positions: Optional[torch.LongTensor],
|
||||
kv_caches: List[torch.Tensor],
|
||||
attn_metadata: AttentionMetadata,
|
||||
intermediate_tensors: Optional[IntermediateTensors] = None,
|
||||
) -> torch.Tensor:
|
||||
output_hidden_states = self.model(
|
||||
input_ids=input_ids,
|
||||
|
||||
Reference in New Issue
Block a user