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

[Models] Add remaining model PP support (#7168)

Browse Source 
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Murali Andoorveedu
2024-10-03 19:56:58 -07:00
committed by GitHub
parent 303d44790a
commit 0f6d7a9a34
69 changed files with 2585 additions and 1344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
vllm/model_executor/models/gpt2.py
View File

@@ -32,8 +32,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
QKVParallelLinear,
RowParallelLinear)
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig)
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead, VocabParallelEmbedding)
@@ -41,7 +40,9 @@ from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from .utils import is_pp_missing_parameter, make_layers
from .interfaces import SupportsPP
from .utils import (is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers)
class GPT2Attention(nn.Module):
@@ -204,6 +205,9 @@ class GPT2Model(nn.Module):
config, cache_config, quant_config, prefix=prefix),
prefix=f"{prefix}.h")
self.ln_f = nn.LayerNorm(self.embed_dim, eps=config.layer_norm_epsilon)
self.make_empty_intermediate_tensors = (
make_empty_intermediate_tensors_factory(["hidden_states"],
config.n_embd))
def forward(
self,
@@ -234,7 +238,7 @@ class GPT2Model(nn.Module):
return hidden_states
class GPT2LMHeadModel(nn.Module):
class GPT2LMHeadModel(nn.Module, SupportsPP):
def __init__(
self,
@@ -256,6 +260,8 @@ class GPT2LMHeadModel(nn.Module):
self.config.hidden_size)
self.logits_processor = LogitsProcessor(config.vocab_size)
self.sampler = Sampler()
self.make_empty_intermediate_tensors = (
self.transformer.make_empty_intermediate_tensors)
def forward(
self,
@@ -264,7 +270,7 @@ class GPT2LMHeadModel(nn.Module):
kv_caches: List[torch.Tensor],
attn_metadata: AttentionMetadata,
intermediate_tensors: Optional[IntermediateTensors] = None,
) -> torch.Tensor:
) -> Union[torch.Tensor, IntermediateTensors]:
hidden_states = self.transformer(input_ids, positions, kv_caches,
attn_metadata, intermediate_tensors)
return hidden_states
@@ -286,16 +292,6 @@ class GPT2LMHeadModel(nn.Module):
next_tokens = self.sampler(logits, sampling_metadata)
return next_tokens
def make_empty_intermediate_tensors(
self, batch_size: int, dtype: torch.dtype,
device: torch.device) -> IntermediateTensors:
return IntermediateTensors({
"hidden_states":
torch.zeros((batch_size, self.config.hidden_size),
dtype=dtype,
device=device),
})
def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
params_dict = dict(self.named_parameters(remove_duplicate=False))
for name, loaded_weight in weights: