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

feat: update linear deps 1/N (#1305)

Browse Source
This commit is contained in:
Yineng Zhang
2024-09-19 20:53:11 +08:00
committed by GitHub
parent 2cd7e181dd
commit b4408b0d16
33 changed files with 1484 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/models/olmoe.py
View File

@@ -35,7 +35,6 @@ from vllm.model_executor.layers.linear import (
ReplicatedLinear,
RowParallelLinear,
)
from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead,
@@ -47,6 +46,7 @@ from vllm.utils import print_warning_once
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.layernorm import RMSNorm
from sglang.srt.layers.logits_processor import LogitsProcessor, LogitsProcessorOutput
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.radix_attention import RadixAttention
from sglang.srt.model_executor.forward_batch_info import InputMetadata