EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Use SGLang imports for linear layer (#1696)

Browse Source
This commit is contained in:
Jani Monoses
2024-10-17 17:50:01 +03:00
committed by GitHub
parent 02f7f3e488
commit 5ab20cceba
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
python/sglang/srt/models/olmo.py
View File

@@ -22,11 +22,6 @@ import torch
from torch import nn from torch import nn
from transformers import OlmoConfig from transformers import OlmoConfig
from vllm.distributed import get_tensor_model_parallel_world_size from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.linear import (
MergedColumnParallelLinear,
QKVParallelLinear,
RowParallelLinear,
)
from vllm.model_executor.layers.rotary_embedding import get_rope from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.vocab_parallel_embedding import ( from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead, ParallelLMHead,
@@ -35,6 +30,11 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
from vllm.model_executor.model_loader.weight_utils import default_weight_loader from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from sglang.srt.layers.activation import SiluAndMul from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.linear import (
MergedColumnParallelLinear,
QKVParallelLinear,
RowParallelLinear,
)
from sglang.srt.layers.logits_processor import LogitsProcessor from sglang.srt.layers.logits_processor import LogitsProcessor
from sglang.srt.layers.quantization.base_config import QuantizationConfig from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.radix_attention import RadixAttention from sglang.srt.layers.radix_attention import RadixAttention