[GH-ISSUE #1088] v0.2.4 post1 编译失败 #766

Open
opened 2026-10-29 14:44:12 +00:00 by bsakaguchi · 8 comments
Owner

Originally created by @TTThanos on GitHub (Apr 8, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1088

今天pull了最新版的KT,按照https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md 中的安装步骤,当运行至 USE_BALANCE_SERVE=1 bash ./install.sh 时,报以下错误,请问该怎么解决
Image

CUDA 12.4
Driver 550
Python 3.10

Originally created by @TTThanos on GitHub (Apr 8, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1088 今天pull了最新版的KT,按照https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md 中的安装步骤,当运行至 `USE_BALANCE_SERVE=1 bash ./install.sh` 时,报以下错误,请问该怎么解决 ![Image](https://github.com/user-attachments/assets/6fc3d7b7-01cc-4e83-9bb5-2919119cc357) CUDA 12.4 Driver 550 Python 3.10
Author
Owner

@ChachAloha commented on GitHub (Apr 8, 2025):

我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译

<!-- gh-comment-id:2787018921 --> @ChachAloha commented on GitHub (Apr 8, 2025): 我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译
Author
Owner

@magikRUKKOLA commented on GitHub (Apr 8, 2025):

Please upgrade your drivers, cuda, python, gcc, g++, gcc and g++ dev libraries outside of your envirtonment too, and everything else! Welcome to the World of Python, the world of ultimate convenience and portability!

https://github.com/kvcache-ai/ktransformers/issues/1051#issuecomment-2785168929

<!-- gh-comment-id:2787592552 --> @magikRUKKOLA commented on GitHub (Apr 8, 2025): Please upgrade your drivers, cuda, python, gcc, g++, gcc and g++ dev libraries outside of your envirtonment too, and everything else! Welcome to the World of Python, the world of ultimate convenience and portability! https://github.com/kvcache-ai/ktransformers/issues/1051#issuecomment-2785168929
Author
Owner

@magikRUKKOLA commented on GitHub (Apr 8, 2025):

我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译

I am sorry, but its simply not true. You can compile its all on your own provided your kept the versions of the software inside and outside of your python environment. I have put the link above -- its totally doable at least on Debian 12. Alternatively, you can listen to the professionals in the field. For example ... https://www.youtube.com/watch?v=YnL9vAFphmE

<!-- gh-comment-id:2787615998 --> @magikRUKKOLA commented on GitHub (Apr 8, 2025): > 我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译 I am sorry, but its simply not true. You can compile its all on your own provided your kept the versions of the software inside and outside of your python environment. I have put the link above -- its totally doable at least on Debian 12. Alternatively, you can listen to the professionals in the field. For example ... https://www.youtube.com/watch?v=YnL9vAFphmE
Author
Owner

@TTThanos commented on GitHub (Apr 9, 2025):

我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译

我用了KT官方的容器build KT也还是不行,容器拉取命令 docker pull approachingai/ktransformers:v0.2.4-AVX512

Image

<!-- gh-comment-id:2788399970 --> @TTThanos commented on GitHub (Apr 9, 2025): > 我环境之前2.3版本也都可以,24开始就不行的重新开了conda,补了依赖也一样,他们说只有官方的容器可以正常编译 我用了KT官方的容器build KT也还是不行,容器拉取命令 `docker pull approachingai/ktransformers:v0.2.4-AVX512` ![Image](https://github.com/user-attachments/assets/6683317c-7800-43ea-9c21-fd90b96bad83)
Author
Owner

@shinchou commented on GitHub (Apr 9, 2025):

sudo apt update && sudo apt install gcc g++ gcc-12 g++-12 build-essential cmake
update-alternatives --install /usr/bin/cc cc /usr/bin/gcc-12 100
update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++-12 100
update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 100
update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 100

<!-- gh-comment-id:2788853058 --> @shinchou commented on GitHub (Apr 9, 2025): sudo apt update && sudo apt install gcc g++ gcc-12 g++-12 build-essential cmake update-alternatives --install /usr/bin/cc cc /usr/bin/gcc-12 100 update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++-12 100 update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 100 update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 100
Author
Owner

@Zhiwei-Dai commented on GitHub (Apr 10, 2025):

也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考:
1、cmake可使用pip安装升级到最新4.0
2、看了B站的视频之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考官方的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh)

<!-- gh-comment-id:2791797159 --> @Zhiwei-Dai commented on GitHub (Apr 10, 2025): 也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考: 1、cmake可使用pip安装升级到最新4.0 2、看了[B站的视频](https://www.bilibili.com/video/BV1czZDYaEZ5?spm_id_from=333.788.player.switch&p=3)之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考[官方](https://kvcache-ai.github.io/ktransformers/en/install.html)的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh)
Author
Owner

@TTThanos commented on GitHub (Apr 11, 2025):

也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考: 1、cmake可使用pip安装升级到最新4.0 2、看了B站的视频之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考官方的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh)

我目前解决了问题,按照https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md 安装指示。
pull了镜像,创建python 3.11 conda环境,安装依赖,重要的是 重新安装了cpufeature到0.2.2版本, 安装flash attention,conda内安装cmake,之后就可以用USE_BALANCE_SERVE=1 bash ./install.sh build 0.2.4 KT了。

机器四卡A10
Ubuntu 22.04
驱动版本570
CUDA 12.8

<!-- gh-comment-id:2796074183 --> @TTThanos commented on GitHub (Apr 11, 2025): > 也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考: 1、cmake可使用pip安装升级到最新4.0 2、看了[B站的视频](https://www.bilibili.com/video/BV1czZDYaEZ5?spm_id_from=333.788.player.switch&p=3)之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考[官方](https://kvcache-ai.github.io/ktransformers/en/install.html)的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh) 我目前解决了问题,按照https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md 安装指示。 pull了镜像,创建python 3.11 conda环境,安装依赖,重要的是 **重新安装了cpufeature到0.2.2版本, 安装flash attention,conda内安装cmake**,之后就可以用`USE_BALANCE_SERVE=1 bash ./install.sh` build 0.2.4 KT了。 机器四卡A10 Ubuntu 22.04 驱动版本570 CUDA 12.8
Author
Owner

@wishfay commented on GitHub (Apr 23, 2025):

也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考: 1、cmake可使用pip安装升级到最新4.0 2、看了B站的视频之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考官方的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh)

我目前解决了问题,按照https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md 安装指示。 pull了镜像,创建python 3.11 conda环境,安装依赖,重要的是 重新安装了cpufeature到0.2.2版本, 安装flash attention,conda内安装cmake,之后就可以用USE_BALANCE_SERVE=1 bash ./install.sh build 0.2.4 KT了。

机器四卡A10 Ubuntu 22.04 驱动版本570 CUDA 12.8

感谢!这样确实可以跑起来了。
需要手动装一下cmake,其实应该算是那个requirement.txt文件少写了一个cmake,如果加上应该也是可以的。

<!-- gh-comment-id:2823342291 --> @wishfay commented on GitHub (Apr 23, 2025): > > 也遇到了这个问题,0.2.3正常,升级到0.2.4报出一堆异常,也定位不到原因。我做了两点尝试,通过了,供参考: 1、cmake可使用pip安装升级到最新4.0 2、看了[B站的视频](https://www.bilibili.com/video/BV1czZDYaEZ5?spm_id_from=333.788.player.switch&p=3)之后,参考脚本执行正常:env USE_BALANCE_SERVE=1 USE_NUMA=1 PYTHONPATH="$(which python)" PATH="$(dirname $(which python)):$PATH" bash ./install.sh。(参考[官方](https://kvcache-ai.github.io/ktransformers/en/install.html)的就是不行:USE_BALANCE_SERVE=1 USE_NUMA=1 bash ./install.sh) > > 我目前解决了问题,按照[https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md](https://2git.xyz/kvcache-ai/ktransformers/blob/main/doc/en/balance-serve.md) 安装指示。 pull了镜像,创建python 3.11 conda环境,安装依赖,重要的是 **重新安装了cpufeature到0.2.2版本, 安装flash attention,conda内安装cmake**,之后就可以用`USE_BALANCE_SERVE=1 bash ./install.sh` build 0.2.4 KT了。 > > 机器四卡A10 Ubuntu 22.04 驱动版本570 CUDA 12.8 感谢!这样确实可以跑起来了。 需要手动装一下cmake,其实应该算是那个requirement.txt文件少写了一个cmake,如果加上应该也是可以的。
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
kvcache-ai/ktransformers#766
No description provided.