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

20
vllm/model_executor/models/deepseek_v2.py
View File

@@ -21,7 +21,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
"""Inference-only DeepseekV2 model."""
from typing import Any, Dict, Iterable, List, Optional, Tuple
from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
import torch
from torch import nn
@@ -40,8 +40,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
ReplicatedLinear,
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.rotary_embedding import get_rope
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
from vllm.model_executor.layers.vocab_parallel_embedding import (
@@ -50,7 +49,9 @@ 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 PPMissingLayer, is_pp_missing_parameter, make_layers
from .interfaces import SupportsPP
from .utils import (PPMissingLayer, is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers)
class DeepseekV2MLP(nn.Module):
@@ -439,6 +440,9 @@ class DeepseekV2Model(nn.Module):
self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
else:
self.norm = PPMissingLayer()
self.make_empty_intermediate_tensors = (
make_empty_intermediate_tensors_factory(
["hidden_states", "residual"], config.hidden_size))
def forward(
self,
@@ -447,7 +451,7 @@ class DeepseekV2Model(nn.Module):
kv_caches: List[torch.Tensor],
attn_metadata: AttentionMetadata,
intermediate_tensors: Optional[IntermediateTensors],
) -> torch.Tensor:
) -> Union[torch.Tensor, IntermediateTensors]:
if get_pp_group().is_first_rank:
hidden_states = self.embed_tokens(input_ids)
residual = None
@@ -472,7 +476,7 @@ class DeepseekV2Model(nn.Module):
return hidden_states
class DeepseekV2ForCausalLM(nn.Module):
class DeepseekV2ForCausalLM(nn.Module, SupportsPP):
def __init__(
self,
@@ -492,6 +496,8 @@ class DeepseekV2ForCausalLM(nn.Module):
quant_config=quant_config)
self.logits_processor = LogitsProcessor(config.vocab_size)
self.sampler = Sampler()
self.make_empty_intermediate_tensors = (
self.model.make_empty_intermediate_tensors)
def forward(
self,
@@ -500,7 +506,7 @@ class DeepseekV2ForCausalLM(nn.Module):
kv_caches: List[torch.Tensor],
attn_metadata: AttentionMetadata,
intermediate_tensors: Optional[IntermediateTensors] = None,
) -> torch.Tensor:
) -> Union[torch.Tensor, IntermediateTensors]:
hidden_states = self.model(input_ids, positions, kv_caches,
attn_metadata, intermediate_tensors)
return hidden_states