kvcache-ai/ktransformers

Fork 0

mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-11-05 01:07:28 +00:00

[GH-ISSUE #420] deepseek r1 using 4090 nvidia running, meet segmentation fault(core dumped) problem #288

New issue

Closed

opened 2026-10-29 14:37:20 +00:00 by bsakaguchi · 5 comments

bsakaguchi commented

2026-10-29 14:37:20 +00:00

Owner

Originally created by @JornShen on GitHub (Feb 17, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/420

cpu: 127
memory: 503G
8*4090

Originally created by @JornShen on GitHub (Feb 17, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/420 ![Image](https://github.com/user-attachments/assets/325f151c-89b2-4bde-8f38-b347456f6346) cpu: 127 memory: 503G 8*4090

bsakaguchi

2026-10-29 14:37:20 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-29 14:37:20 +00:00

Author

Owner

@JornShen commented on GitHub (Feb 17, 2025):

(gdb)
#0 0x00007f84d9ba2ab8 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#1 0x00007f84d9ba8be8 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#2 0x00007f84d9b4f506 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#3 0x00007f84d9ba58f5 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#4 0x00007f84d9ba837a in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#5 0x00007f84d9ba8443 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so
#6 0x00007fa3c3828bf4 in std::execute_native_thread_routine (__p=0xc037d10) at /opt/conda/conda-bld/gcc-compiler_1654084175708/work/gcc/libstdc++-v3/src/c++11/thread.cc:82
#7 0x00007fa4177d2609 in start_thread (arg=) at pthread_create.c:477
#8 0x00007fa41759d353 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95

@JornShen commented on GitHub (Feb 17, 2025): (gdb) #0 0x00007f84d9ba2ab8 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #1 0x00007f84d9ba8be8 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #2 0x00007f84d9b4f506 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #3 0x00007f84d9ba58f5 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #4 0x00007f84d9ba837a in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #5 0x00007f84d9ba8443 in ?? () from /opt/conda/envs/ktransformers/lib/python3.11/site-packages/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so #6 0x00007fa3c3828bf4 in std::execute_native_thread_routine (__p=0xc037d10) at /opt/conda/conda-bld/gcc-compiler_1654084175708/work/gcc/libstdc++-v3/src/c++11/thread.cc:82 #7 0x00007fa4177d2609 in start_thread (arg=<optimized out>) at pthread_create.c:477 #8 0x00007fa41759d353 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95

bsakaguchi commented

2026-10-29 14:37:21 +00:00

Author

Owner

@GodXuxilie commented on GitHub (Feb 18, 2025):

i also met the issue on H100

@GodXuxilie commented on GitHub (Feb 18, 2025): i also met the issue on H100

bsakaguchi commented

2026-10-29 14:37:21 +00:00

Author

Owner

@lililolo0927 commented on GitHub (Feb 19, 2025):

Same for me (4090) on container when I run R1 on chat uing the following cmd:
python -m ktransformers.local_chat --gguf_path /models/gguf/DeepSeek-R1-GGUF --model_path deepseek-ai/DeepSeek-R1

Anyone solve this pb?

@lililolo0927 commented on GitHub (Feb 19, 2025): Same for me (4090) on container when I run R1 on chat uing the following cmd: python -m ktransformers.local_chat --gguf_path /models/gguf/DeepSeek-R1-GGUF --model_path deepseek-ai/DeepSeek-R1 ![Image](https://github.com/user-attachments/assets/07d740ca-4f3d-406d-a553-20971e11b132) Anyone solve this pb?

bsakaguchi commented

2026-10-29 14:37:21 +00:00

Author

Owner

@zwbsxwt commented on GitHub (Feb 25, 2025):

我也遇到了这个问题，在docker环境中，运行其他模型(例如：Qwen2-57B-GGUF)是可以的
R1_Q4就是不行
硬件环境： 1T内存
显卡： 4* RTX4090
Cpu: 2 * Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz

问题解决了,我的是模型文件损坏了,计算了sha 256值发现一个不一样,重新下载就好了

@zwbsxwt commented on GitHub (Feb 25, 2025): 我也遇到了这个问题，在docker环境中，运行其他模型(例如：Qwen2-57B-GGUF)是可以的 R1_Q4就是不行硬件环境： 1T内存显卡： 4* RTX4090 Cpu: 2 * Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz ------------------------- 问题解决了,我的是模型文件损坏了,计算了sha 256值发现一个不一样,重新下载就好了

bsakaguchi commented

2026-10-29 14:37:21 +00:00

Author

Owner

@ErvinXie commented on GitHub (Dec 11, 2025):

This issue has been automatically closed due to inactivity for 60 days.

If you believe this issue is still relevant, please feel free to reopen it with additional information or context.

Thank you for your contribution to KTransformers!

此 issue 因超过 60 天无活动而被自动关闭。

如果您认为此问题仍然存在，请随时重新打开并提供更多信息或上下文。

感谢您对 KTransformers 的贡献！

@ErvinXie commented on GitHub (Dec 11, 2025): This issue has been automatically closed due to inactivity for 60 days. If you believe this issue is still relevant, please feel free to reopen it with additional information or context. Thank you for your contribution to KTransformers! --- 此 issue 因超过 60 天无活动而被自动关闭。如果您认为此问题仍然存在，请随时重新打开并提供更多信息或上下文。感谢您对 KTransformers 的贡献！