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

feat: remove vllm distributed (#2907)

Browse Source 
Co-authored-by: Zhangyi <1109276519@qq.com>
This commit is contained in:
Yineng Zhang
2025-01-17 22:31:51 +08:00
committed by GitHub
parent f3e9b4894b
commit 5dc54f1a62
45 changed files with 111 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/layers/quantization/fp8.py
View File

@@ -8,7 +8,6 @@ import torch.nn.functional as F
from torch.nn import Module
from torch.nn.parameter import Parameter
from vllm import _custom_ops as ops
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
from vllm.model_executor.layers.quantization.utils.marlin_utils_fp8 import (
apply_fp8_marlin_linear,
@@ -24,6 +23,7 @@ from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
requantize_with_max_scale,
)
from sglang.srt.distributed import get_tensor_model_parallel_world_size
from sglang.srt.layers.linear import (
LinearBase,
LinearMethodBase,