CPU本地加载GPT-OSS-20B模型时遭遇KeyError问题求助

我现在尝试在纯CPU环境下用Hugging Face Transformers本地加载gpt-oss-20B模型，但遇到了一个KeyError问题，折腾了好久没解决，来求助大家！

我的最小复现代码 #

from transformers import pipeline
model_path = "/mnt/d/Projects/models/gpt-oss-20b"
pipe = pipeline("text-generation", model=model_path, torch_dtype="auto", device_map="auto")
pipe("Hello", max_new_tokens=20)

报错信息及关键日志 #

运行后首先输出了这些提示：

Using MXFP4 quantized models requires a GPU, we will default to dequantizing the model to bf16
Loading checkpoint shards: 100%
Some parameters are on the meta device because they were offloaded to the cpu and disk.
Device set to use cpu

然后就抛出了KeyError：

Traceback (most recent call last):
  File "/home/dev/projects/wolf-in-ai-clothing/convo_test.py", line 19, in invoke
    response = model(user_message, max_new_tokens=20, num_return_sequences=1)
  File ".../transformers/pipelines/text_generation.py", line 419, in _forward
    output = self.model.generate(input_ids=input_ids, attention_mask=attention_mask, **generate_kwargs)
  File ".../transformers/models/gpt_oss/modeling_gpt_oss.py", line 375, in forward
    hidden_states, _ = self.mlp(hidden_states) # diff with llama: router scores
  File ".../transformers/models/gpt_oss/modeling_gpt_oss.py", line 159, in forward
    routed_out = self.experts(hidden_states, router_indices=router_indices, routing_weights=router_scores)
  File ".../accelerate/utils/offload.py", line 118, in __getitem__
    return self.dataset[f"{self.prefix}{key}"]
  File ".../accelerate/utils/offload.py", line 165, in __getitem__
    weight_info = self.index[key]
KeyError: 'model.layers.5.mlp.experts.gate_up_proj'

我已经确认模型目录是存在的，里面的模型文件也都齐全。之前在Hugging Face论坛看到过类似问题，跟着@noobaymax的建议试了这些操作：

• 安装triton主分支版本：pip install git+https://github.com/triton-lang/triton.git@main#subdirectory=python/triton_kernels
• 安装transformers的最新开发版：pip install git+https://github.com/huggingface/transformers.git
• 安装相关kernel依赖（跟着步骤执行，但未明确具体包名）

但执行完这些后，问题还是完全一样，没有任何改善。

我的环境信息 #

• Python：3.12.3
• Transformers：4.56.0.dev0（也试过稳定版4.55.1）
• PyTorch：2.8.0
• Accelerate：1.10.0
• 系统：WSL2上的Ubuntu 22.04，无GPU，32GB RAM

有没有大佬遇到过类似的问题？或者知道纯CPU环境下正确加载这个模型的方法？麻烦指点一下！

内容来源于stack exchange