chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[1/N] Remove CacheConfig import in all model files (#1658)

Browse Source
This commit is contained in:
Byron Hsu
2024-10-14 09:06:34 -07:00
committed by GitHub
parent 02bc95796d
commit 56503d9bc9
30 changed files with 64 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
python/sglang/srt/models/chatglm.py
View File

@@ -22,7 +22,6 @@ from typing import Iterable, Optional, Tuple
import torch
from torch import nn
from torch.nn import LayerNorm
from vllm.config import CacheConfig
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.vocab_parallel_embedding import (
@@ -52,7 +51,7 @@ class GLMAttention(nn.Module):
self,
config,
layer_id: int = 0,
cache_config: Optional[CacheConfig] = None,
cache_config=None,
quant_config: Optional[QuantizationConfig] = None,
):
super().__init__()
@@ -188,7 +187,7 @@ class GLMBlock(nn.Module):
self,
config,
layer_id: int,
cache_config: Optional[CacheConfig] = None,
cache_config=None,
quant_config: Optional[QuantizationConfig] = None,
):
super().__init__()
@@ -260,7 +259,7 @@ class GLMTransformer(nn.Module):
def __init__(
self,
config,
cache_config: Optional[CacheConfig] = None,
cache_config=None,
quant_config: Optional[QuantizationConfig] = None,
):
super().__init__()
@@ -308,7 +307,7 @@ class ChatGLMModel(nn.Module):
def __init__(
self,
config,
cache_config: Optional[CacheConfig] = None,
cache_config=None,
quant_config: Optional[QuantizationConfig] = None,
):
super().__init__()
@@ -359,7 +358,7 @@ class ChatGLMForCausalLM(nn.Module):
def __init__(
self,
config: ChatGLMConfig,
cache_config: Optional[CacheConfig] = None,
cache_config=None,
quant_config: Optional[QuantizationConfig] = None,
lora_config: Optional[LoraConfig] = None,
):