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

24
vllm/model_executor/models/jais.py
View File

@@ -33,8 +33,7 @@ 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)
@@ -43,7 +42,9 @@ from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from vllm.transformers_utils.configs import JAISConfig
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 SwiGLUActivation(nn.Module):
@@ -244,6 +245,9 @@ class JAISModel(nn.Module):
)
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,
@@ -279,7 +283,7 @@ class JAISModel(nn.Module):
return hidden_states
class JAISLMHeadModel(nn.Module):
class JAISLMHeadModel(nn.Module, SupportsPP):
def __init__(
self,
@@ -304,6 +308,8 @@ class JAISLMHeadModel(nn.Module):
self.logits_processor = LogitsProcessor(vocab_size=config.vocab_size,
scale=self.output_logits_scale)
self.sampler = Sampler()
self.make_empty_intermediate_tensors = (
self.transformer.make_empty_intermediate_tensors)
def forward(
self,
@@ -326,16 +332,6 @@ class JAISLMHeadModel(nn.Module):
sampling_metadata)
return logits
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 sample(
self,
logits: torch.Tensor,