kvcache-ai / kvcache-ai/ktransformers
[Bug] 编译失败,在custom_flashinfer部分一直无法正常安装,已多次尝试
- Dominant language
- Python
- Stars
- 19.5k
- Forks
- 1.6k
- Avg merge
- 19h 32m
- Merged PRs (30d)
- 27
Description
### 检查清单
- [x] 1. 我已经搜索过相关问题,但未能获得预期的帮助
- [x] 2. 该问题在最新版本中尚未修复
- [x] 3. 请注意,如果您提交的BUG相关 issue 缺少对应环境信息和最小可复现示例,我们将难以复现和定位问题,降低获得反馈的可能性
- [x] 4. 如果您提出的不是bug而是问题,请在讨论区发起讨论 https://github.com/kvcache-ai/ktransformers/discussions。否则该 issue 将被关闭
- [x] 5. 为方便社区交流,我将使用中文/英文或附上中文/英文翻译(如使用其他语言)。未附带翻译的非中文/英语内容可能会被关闭
### 问题描述
完整编译过程见附件
[custom_flashinfer_err.txt](https://github.com/user-attachments/files/20459290/custom_flashinfer_err.txt)
[ 95%] Built target sched
/usr/bin/gmake -f sched/CMakeFiles/sched_ext.dir/build.make sched/CMakeFiles/sched_ext.dir/depend
gmake[2]: 进入目录“/root/ktransformers/csrc/balance_serve/build”
cd /root/ktransformers/csrc/balance_serve/build && /usr/bin/cmake -E cmake_depends "Unix Makefiles" /root/ktransformers/csrc/balance_serve /root/ktransformers/csrc/balance_serve/sched /root/ktransformers/csrc/balance_serve/build /root/ktransformers/csrc/balance_serve/build/sched /root/ktransformers/csrc/balance_serve/build/sched/CMakeFiles/sched_ext.dir/DependInfo.cmake --color=
Dependencies file "sched/CMakeFiles/sched_ext.dir/bind.cpp.o.d" is newer than depends file "/root/ktransformers/csrc/balance_serve/build/sched/CMakeFiles/sched_ext.dir/compiler_depend.internal".
Consolidate compiler generated dependencies of target sched_ext
gmake[2]: 离开目录“/root/ktransformers/csrc/balance_serve/build”
/usr/bin/gmake -f sched/CMakeFiles/sched_ext.dir/build.make sched/CMakeFiles/sched_ext.dir/build
gmake[2]: 进入目录“/root/ktransformers/csrc/balance_serve/build”
[ 97%] Linking CXX shared module /tmp/tmp41s3_mwa.build-lib/sched_ext.cpython-311-x86_64-linux-gnu.so
cd /root/ktransformers/csrc/balance_serve/build/sched && /usr/bin/cmake -E cmake_link_script CMakeFiles/sched_ext.dir/link.txt --verbose=1
/usr/bin/g++-11 -fPIC -Og -march=native -Wall -Wextra -g -fPIC -O3 -DNDEBUG -flto -shared -o /tmp/tmp41s3_mwa.build-lib/sched_ext.cpython-311-x86_64-linux-gnu.so CMakeFiles/sched_ext.dir/bind.cpp.o -L/lib/intel64 -L/lib/intel64_win -L/lib/win-x64 -Wl,-rpath,/lib/intel64:/lib/intel64_win:/lib/win-x64:/tmp/tmp41s3_mwa.build-lib:/root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib:/usr/local/cuda/lib64:/root/ktransformers/csrc/balance_serve/build/third_party/prometheus-cpp/lib /tmp/tmp41s3_mwa.build-lib/libsched.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10.so /usr/local/cuda/lib64/libnvrtc.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10_cuda.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libtorch_python.so /tmp/tmp41s3_mwa.build-lib/libkvc2.so /usr/lib/x86_64-linux-gnu/libtbb.so.12.5 /tmp/tmp41s3_mwa.build-lib/libcache_entry.so /tmp/tmp41s3_mwa.build-lib/libgpu_cache.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libtorch.so -Wl,--no-as-needed,"/root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libtorch_cpu.so" -Wl,--as-needed -Wl,--no-as-needed,"/root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libtorch_cuda.so" -Wl,--as-needed /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10_cuda.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10.so -Wl,--no-as-needed,"/root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libtorch.so" -Wl,--as-needed /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10.so /usr/local/cuda/lib64/libnvrtc.so /usr/local/cuda/lib64/libnvToolsExt.so /root/miniconda3/envs/kt/lib/python3.11/site-packages/torch/lib/libc10_cuda.so ../third_party/xxHash/libxxhash.a /tmp/tmp41s3_mwa.build-lib/libcuda_stream_manager.so /usr/local/cuda/lib64/libcudart.so /tmp/tmp41s3_mwa.build-lib/libpage_aligned_memory_pool.so ../kvc2/src/libkvc2_metrics.a /tmp/tmp41s3_mwa.build-lib/libasync_store.so -lpthread /tmp/tmp41s3_mwa.build-lib/libsched_metrics.so ../third_party/prometheus-cpp/lib/libprometheus-cpp-pull.so.1.3.0 ../third_party/prometheus-cpp/lib/libprometheus-cpp-core.so.1.3.0
lto-wrapper: warning: using serial compilation of 6 LTRANS jobs
cd /root/ktransformers/csrc/balance_serve/build/sched && /usr/bin/strip /tmp/tmp41s3_mwa.build-lib/sched_ext.cpython-311-x86_64-linux-gnu.so
gmake[2]: 离开目录“/root/ktransformers/csrc/balance_serve/build”
[100%] Built target sched_ext
gmake[1]: 离开目录“/root/ktransformers/csrc/balance_serve/build”
/usr/bin/cmake -E cmake_progress_start /root/ktransformers/csrc/balance_serve/build/CMakeFiles 0
CMake args: ['-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/tmp/tmp41s3_mwa.build-lib/', '-DPYTHON_EXECUTABLE=/root/miniconda3/envs/kt/bin/python3.11', '-DCMAKE_BUILD_TYPE=Release', '-DKTRANSFORMERS_USE_CUDA=ON', '-D_GLIBCXX_USE_CXX11_ABI=1']
CMake args: ['-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/tmp/tmp41s3_mwa.build-lib/', '-DPYTHON_EXECUTABLE=/root/miniconda3/envs/kt/bin/python3.11', '-DCMAKE_BUILD_TYPE=Release', '-DKTRANSFORMERS_USE_CUDA=ON', '-D_GLIBCXX_USE_CXX11_ABI=1', '-DLLAMA_NATIVE=ON', '-DEXAMPLE_VERSION_INFO=0.3.1+cu128torch27avx2']
build_temp: /root/ktransformers/csrc/balance_serve/build
copying /tmp/tmp41s3_mwa.build-lib/cpuinfer_ext.cpython-311-x86_64-linux-gnu.so ->
copying /tmp/tmp41s3_mwa.build-lib/KTransformersOps.cpython-311-x86_64-linux-gnu.so ->
copying /tmp/tmp41s3_mwa.build-lib/vLLMMarlin.cpython-311-x86_64-linux-gnu.so ->
error: can't copy '/tmp/tmp41s3_mwa.build-lib/balance_serve.cpython-311-x86_64-linux-gnu.so': doesn't exist or not a regular file
error: subprocess-exited-with-error
× Building editable for ktransformers (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip.
full command: /root/miniconda3/envs/kt/bin/python3.11 /root/miniconda3/envs/kt/lib/python3.11/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_editable /tmp/tmprj8ag6ui
cwd: /root/ktransformers
Building editable for ktransformers (pyproject.toml) ... error
ERROR: Failed building editable for ktransformers
Failed to build flashinfer-python ktransformers
ERROR: Failed to build installable wheels for some pyproject.toml based projects (flashinfer-python, ktransformers)
### 复现步骤
pip install third_party/custom_flashinfer/ -e . -v
### 环境信息
代码是直接 git clone https://github.com/kvcache-ai/ktransformers.git --recursive
CPU 双路 7641
GPU 3090
文件系统剩余400G
内存1024G
系统 ubuntu22.04
cuda 12.8
驱动 NVIDIA-Linux-x86_64-570.144
nvcc --version # 12.8
g++ --version #11.4.0
gcc --version #11.4.0
cmake --version #3.22.1
ninja --version #1.11.1.git.kitware.jobserver-1
pip list
accelerate 1.7.0
annotated-types 0.7.0
anyio 4.9.0
blessed 1.21.0
blobfile 3.0.0
build 1.2.2.post1
certifi 2025.4.26
charset-normalizer 3.4.2
click 8.2.1
colorlog 6.9.0
cpufeature 0.2.1
distro 1.9.0
einops 0.8.1
fastapi 0.115.12
filelock 3.13.1
fire 0.7.0
flash_attn 2.7.4.post1 #https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp311-cp311-linux_x86_64.whl
fsspec 2024.6.1
greenlet 3.2.2
h11 0.16.0
hf-xet 1.1.2
httpcore 1.0.9
httpx 0.28.1
huggingface-hub 0.32.2
idna 3.10
Jinja2 3.1.4
jiter 0.10.0
jsonpatch 1.33
jsonpointer 3.0.0
ktransformers 0.3.1+cu128torch27avx2
langchain 0.3.25
langchain-core 0.3.61
langchain-text-splitters 0.3.8
langsmith 0.3.42
lxml 5.4.0
MarkupSafe 2.1.5
mpmath 1.3.0
networkx 3.3
ninja 1.11.1.4
numpy 2.1.2
nvidia-cublas-cu12 12.8.3.14
nvidia-cuda-cupti-cu12 12.8.57
nvidia-cuda-nvrtc-cu12 12.8.61
nvidia-cuda-runtime-cu12 12.8.57
nvidia-cudnn-cu12 9.7.1.26
nvidia-cufft-cu12 11.3.3.41
nvidia-cufile-cu12 1.13.0.11
nvidia-curand-cu12 10.3.9.55
nvidia-cusolver-cu12 11.7.2.55
nvidia-cusparse-cu12 12.5.7.53
nvidia-cusparselt-cu12 0.6.3
nvidia-nccl-cu12 2.26.2
nvidia-nvjitlink-cu12 12.8.61
nvidia-nvtx-cu12 12.8.55
openai 1.82.0
orjson 3.10.18
packaging 24.2
pillow 11.0.0
pip 25.1
protobuf 6.31.0
psutil 7.0.0
pycryptodomex 3.23.0
pydantic 2.11.5
pydantic_core 2.33.2
pyproject_hooks 1.2.0
PyYAML 6.0.2
pyzmq 26.4.0
regex 2024.11.6
requests 2.32.3
requests-toolbelt 1.0.0
safetensors 0.5.3
sentencepiece 0.2.0
setuptools 78.1.1
sniffio 1.3.1
SQLAlchemy 2.0.41
starlette 0.46.2
sympy 1.13.3
tenacity 9.1.2
termcolor 3.1.0
tiktoken 0.9.0
tokenizers 0.21.1
torch 2.7.0+cu128
torchaudio 2.7.0+cu128
torchvision 0.22.0+cu128
tqdm 4.67.1
transformers 4.51.3
triton 3.3.0
typing_extensions 4.12.2
typing-inspection 0.4.1
urllib3 2.4.0
uvicorn 0.34.2
wcwidth 0.2.13
wheel 0.45.1
zmq 0.0.0
zstandard 0.23.0
Contributor guide
Assessment
This issue has not been assessed yet.