mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #1736] 为什么我安装的kt没有./server目录 #1099
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#1099
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @enochday on GitHub (Dec 21, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1736
Reminder
System Info
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4070 Off | 00000000:01:00.0 On | N/A |
| 0% 40C P8 13W / 200W | 845MiB / 12282MiB | 7% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 2041 G /usr/lib/xorg/Xorg 380MiB |
| 0 N/A N/A 2200 G /usr/bin/gnome-shell 73MiB |
| 0 N/A N/A 3617 G ...rack-uuid=3190708988185955192 278MiB |
| 0 N/A N/A 7645 G /usr/share/code/code 67MiB |
+-----------------------------------------------------------------------------------------+
Reproduction
我使用docker安装好KTransformers0.4.3后，按照这个文档尝试运行Qwen3-Next Qwen3-Next.md 提示没有./server/main.py
复现方式：
输出：
我重新git clone了一遍，发现仍然没有./server/main.py
Others
No response
@enochday commented on GitHub (Dec 21, 2025):
我用git clone了一个0.4.1的老版本，发现这个版本是有./server的。但是新版本似乎移除了./server，我尝试使用sglang运行Qwen3 Next，提示不支持
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "/workspace/sglang/python/sglang/launch_server.py", line 24, in
server_args = prepare_server_args(sys.argv[1:])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/sglang/python/sglang/srt/server_args.py", line 4001, in prepare_server_args
return ServerArgs.from_cli_args(raw_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/sglang/python/sglang/srt/server_args.py", line 3616, in from_cli_args
return cls(**{attr: getattr(args, attr) for attr in attrs})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 276, in init
File "/workspace/sglang/python/sglang/srt/server_args.py", line 596, in post_init
self._handle_model_specific_adjustments()
File "/workspace/sglang/python/sglang/srt/server_args.py", line 901, in _handle_model_specific_adjustments
hf_config = self.get_hf_config()
^^^^^^^^^^^^^^^^^^^^
File "/workspace/sglang/python/sglang/srt/server_args.py", line 3626, in get_hf_config
hf_config = get_config(
^^^^^^^^^^^
File "/workspace/sglang/python/sglang/srt/utils/common.py", line 3101, in wrapper
result = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/workspace/sglang/python/sglang/srt/utils/hf_transformers_utils.py", line 219, in get_config
raise e
File "/workspace/sglang/python/sglang/srt/utils/hf_transformers_utils.py", line 213, in get_config
config = AutoConfig.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/miniconda3/envs/serve/lib/python3.12/site-packages/transformers/models/auto/configuration_auto.py", line 1332, in from_pretrained
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/miniconda3/envs/serve/lib/python3.12/site-packages/transformers/configuration_utils.py", line 662, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/miniconda3/envs/serve/lib/python3.12/site-packages/transformers/configuration_utils.py", line 753, in _get_config_dict
config_dict = load_gguf_checkpoint(resolved_config_file, return_tensors=False)["config"]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/miniconda3/envs/serve/lib/python3.12/site-packages/transformers/modeling_gguf_pytorch_utils.py", line 431, in load_gguf_checkpoint
raise ValueError(f"GGUF model with architecture {architecture} is not supported yet.")
ValueError: GGUF model with architecture qwen3next is not supported yet.
@enochday commented on GitHub (Dec 21, 2025):
已经解决了，抱歉我没找到正确的位置。新版的Ktransformers把server目录放在了./archive/ktransformers/server