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

8
vllm/model_executor/models/granite.py
View File

@@ -51,7 +51,7 @@ from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from vllm.utils import is_hip
from .interfaces import SupportsLoRA
from .interfaces import SupportsLoRA, SupportsPP
from .utils import PPMissingLayer, is_pp_missing_parameter, make_layers
@@ -311,13 +311,13 @@ class GraniteModel(nn.Module):
else:
hidden_states = self.get_input_embeddings(input_ids)
residual = None
hidden_states *= self.config.embedding_multiplier
else:
assert intermediate_tensors is not None
hidden_states = intermediate_tensors["hidden_states"]
residual = intermediate_tensors["residual"]
hidden_states *= self.config.embedding_multiplier
for i in range(self.start_layer, self.end_layer):
layer = self.layers[i]
hidden_states = layer(
@@ -337,7 +337,7 @@ class GraniteModel(nn.Module):
return hidden_states
class GraniteForCausalLM(nn.Module, SupportsLoRA):
class GraniteForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
packed_modules_mapping = {
"qkv_proj": [
"q_proj",