Lychee X
Lychee X
hello , 使用简单的代码也能复现这个bug, from transformers import AutoTokenizer from vllm import LLM, SamplingParams # GLM-4-9B-Chat-1M # max_model_len, tp_size = 1048576, 4 # 如果遇见 OOM 现象,建议减少max_model_len,或者增加tp_size max_model_len, tp_size = 131072, 1 model_name...
dtype 改为float16后出现 ttributeError: '_OpNamespace' '_C' object has no attribute 'rms_norm'
same to you , what's the matter ?
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 8 but got size 4 for tensor number 1 in the list.
dear 大佬, 赶紧搞上去,整个gradio demo,thx
抱歉,网络延迟导致创建了另外的issue,另一个已经关闭,以这个为主。
 提示词:a photo of two people img , These two people are in the same picture, with the man standing next to the woman.The clothing style remains unchanged. 生成的还是没有保持原样。太随机了。怎么控制?
有没有大佬帮帮忙啊?
Package Version ------------------------ ------------ accelerate 1.8.1 aiofiles 24.1.0 albucore 0.0.24 albumentations 2.0.8 annotated-types 0.7.0 antlr4-python3-runtime 4.9.3 anyio 4.9.0 certifi 2025.6.15 charset-normalizer 3.4.2 click 8.2.1 coloredlogs 15.0.1 contourpy 1.3.2 cycler 0.12.1...