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

16
python/sglang/srt/models/commandr.py
View File

@@ -50,21 +50,21 @@ from vllm.distributed import (
get_tensor_model_parallel_rank,
get_tensor_model_parallel_world_size,
)
from vllm.model_executor.layers.linear import (
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.vocab_parallel_embedding import VocabParallelEmbedding
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.linear import (
MergedColumnParallelLinear,
QKVParallelLinear,
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 VocabParallelEmbedding
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.utils import set_weight_attrs
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.logits_processor import LogitsProcessor
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
from sglang.srt.utils import set_weight_attrs
@torch.compile