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/llama_classification.py
View File

@@ -19,10 +19,10 @@ import torch
from torch import nn
from transformers import LlamaConfig
from vllm.config import CacheConfig
from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from sglang.srt.layers.logits_processor import LogitsProcessorOutput
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.model_executor.forward_batch_info import InputMetadata
from sglang.srt.models.llama import LlamaForCausalLM, LlamaModel