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

Update model_loader deps and qqq quantization deps (#2220) (#2318)

Browse Source 
Co-authored-by: HandH1998 <1335248067@qq.com>
This commit is contained in:
Yineng Zhang
2024-12-02 23:22:13 +08:00
committed by GitHub
parent 33deca81b5
commit 85e1a6f3aa
58 changed files with 2363 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/models/xverse.py
View File

@@ -30,7 +30,6 @@ from vllm.model_executor.layers.linear import (
RowParallelLinear,
)
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from sglang.srt.layers.logits_processor import LogitsProcessor
from sglang.srt.layers.quantization.base_config import QuantizationConfig
@@ -40,6 +39,7 @@ from sglang.srt.layers.vocab_parallel_embedding import (
VocabParallelEmbedding,
)
from sglang.srt.model_executor.model_runner import ForwardBatch
from sglang.srt.model_loader.weight_utils import default_weight_loader
class XverseMLP(nn.Module):
@@ -295,8 +295,6 @@ class XverseForCausalLM(nn.Module):
self,
config: LlamaConfig,
quant_config: Optional[QuantizationConfig] = None,
cache_config=None,
efficient_weight_load=False,
) -> None:
super().__init__()
self.config = config