zhizi42
zhizi42
similar crash log, hope update😭
similar issue, when use qwen2 `AttributeError: 'Qwen2MoeForCausalLM' object has no attribute '_prepare_generation_config'` with wsl
> on latest 3.2 im getting a key error with single concurrency. > > ``` > Traceback (most recent call last): > File "/home/pharrow/ktransformers/ktransformers/server/main.py", line 122, in > main() >...
使用 `pip install -U transformers` 似乎解决了ModuleNotFoundError: No module named 'transformers.masking_utils问题 但还是会出现 `ValueError: You should provide exactly one of `layers` or `layer_class_to_replicate` to initialize a Cache.`
研究了几天发现其实很简单，在开始git clone的时候改为clone指定版本就行了 `git clone --branch v0.3.2 https://github.com/kvcache-ai/ktransformers.git`
5080也是 ValueError: You should provide exactly one of layers or layer_class_to_replicate to initialize a Cache. 这个问题，transformers=4.57.0，ktransformers=0.3.2+cu128torch28avx2，cuda12.8，torch2.8.0 尝试了4060ti也是这个问题，有人知道如何解决吗
研究了几天发现其实很简单，在开始git clone的时候改为clone指定版本就行了 `git clone --branch v0.3.2 https://github.com/kvcache-ai/ktransformers.git`