[Feature] 0.3.2的最新版目前支持deepseek的哪些动态量化版本？

### Checklist

- [ ] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed.
- [ ] 2. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-English/Chinese content without translation may be closed.

### Motivation

我编译安装了KT0.3.2，尝试运行Deepseek-R1-671B-0528-IQ2_M版本，但是在加载模型过程中，我发现内存使用量并没有增加，通过debug，发现MOE层的参数全都是元数据，只有CUDA层的参数被真正加载，显存也有占用，CUDA Graph构建过程正常，最后卡在输出第一个字之前，过一会还会报错：
Traceback (most recent call last):
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/backend/interfaces/balance_serve.py", line 313, in run_engine
engine.loop()
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/backend/interfaces/balance_serve.py", line 265, in loop
self.model_runner.run(self.batch, self.query_manager)
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/balance_serve/inference/model_runner.py", line 194, in run
self.features = self.model.batch_embeddings(self.input[cuda_graph_idx], device=self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/models/custom_modeling_deepseek_v3.py", line 66, in batch_embeddings
self.model.embed_tokens(tokens.to(torch.device('cpu')))
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/torch/nn/modules/sparse.py", line 192, in forward
return F.embedding(
^^^^^^^^^^^^
File "/home/wangqs/miniconda3/envs/ktransformers/lib/python3.11/site-packages/torch/nn/functional.py", line 2546, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index out of range in self

一个比较重要的问题是，我只有家用平台，256GB内存，KT目前为止支持哪些动态量化版本？我好选择性能和内存较平衡的版本。

### Related resources

_No response_

Start by reproducing the DeepSeek-R1-671B-0528-IQ2_M load and trace the failure through server/backend/interfaces/balance_serve.py, balance_serve/inference/model_runner.py, and models/custom_modeling_deepseek_v3.py. Check how supported dynamic quantization formats are selected and whether the reported embedding index error is reproducible; done means the supported versions and any compatibility limitation are documented or the failing model loads successfully.

Written by the indexing model from the issue text.