[GH-ISSUE #1524] [Bug] Compile Error: no such instruction: `vpdpbssd 2(%r9,%rax),%ymm4,%ymm1' #1020

New issue

Open

opened 2026-10-29 14:47:32 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-29 14:47:32 +00:00

Owner

Originally created by @zzningxp on GitHub (Oct 16, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1524

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed.
5. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-Chinese/English content without translation may be closed.

Describe the bug

When compile using bash install.sh, with git head d44800c, on CPU: Intel(R) Core(TM) Ultra 7 265K (without avx512 support) + RTX5080 CUDA12.8:

cd /home/Develop/ktransformers/csrc/ktransformers_ext/build/third_party/llama.cpp && /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GLIBCXX_USE_CXX11_ABI=1 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -D__x86_64__ -I/home/daodao/Develop/ktransformers/third_party/llama.cpp/. -O3 -ffast-math -fopenmp -O3 -DNDEBUG -std=gnu++11 -fPIC -mfma -mavx -mavx2 -march=native -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -fopenmp -MD -MT third_party/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o -MF CMakeFiles/ggml.dir/sgemm.cpp.o.d -o CMakeFiles/ggml.dir/sgemm.cpp.o -c /home/daodao/Develop/ktransformers/third_party/llama.cpp/sgemm.cpp
  /tmp/cc7ghyo2.s: Assembler messages:
  /tmp/cc7ghyo2.s:31723: Error: no such instruction: `vpdpbssd -32(%r9),%ymm0,%ymm2'
  /tmp/cc7ghyo2.s:31863: Error: no such instruction: `vpdpbssd -32(%r9),%ymm0,%ymm1'
  /tmp/cc7ghyo2.s:31998: Error: no such instruction: `vpdpbssd 2(%r9,%rax),%ymm4,%ymm1'
  gmake[2]: *** [third_party/llama.cpp/CMakeFiles/ggml.dir/build.make:121: third_party/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o] Error 1
  gmake[2]: *** Waiting for unfinished jobs....
  gmake[2]: Leaving directory '/home/daodao/Develop/ktransformers/csrc/ktransformers_ext/build'
  gmake[1]: *** [CMakeFiles/Makefile2:264: third_party/llama.cpp/CMakeFiles/ggml.dir/all] Error 2
  gmake[1]: *** Waiting for unfinished jobs....
  [ 38%] Linking CXX static library libllamafile.a
  /usr/local/bin/cmake -P CMakeFiles/llamafile.dir/cmake_clean_target.cmake
  /usr/local/bin/cmake -E cmake_link_script CMakeFiles/llamafile.dir/link.txt --verbose=1```



### Reproduction

bash install.sh

### Environment

 CPU: Intel(R) Core(TM) Ultra 7 265K (without avx512 support) + RTX5080 CUDA12.8

Originally created by @zzningxp on GitHub (Oct 16, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1524 ### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version. - [ ] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback. - [ ] 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed. - [ ] 5. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-Chinese/English content without translation may be closed. ### Describe the bug When compile using `bash install.sh`, with git head d44800c, on CPU: Intel(R) Core(TM) Ultra 7 265K (without avx512 support) + RTX5080 CUDA12.8: ``` cd /home/Develop/ktransformers/csrc/ktransformers_ext/build/third_party/llama.cpp && /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GLIBCXX_USE_CXX11_ABI=1 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -D__x86_64__ -I/home/daodao/Develop/ktransformers/third_party/llama.cpp/. -O3 -ffast-math -fopenmp -O3 -DNDEBUG -std=gnu++11 -fPIC -mfma -mavx -mavx2 -march=native -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -fopenmp -MD -MT third_party/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o -MF CMakeFiles/ggml.dir/sgemm.cpp.o.d -o CMakeFiles/ggml.dir/sgemm.cpp.o -c /home/daodao/Develop/ktransformers/third_party/llama.cpp/sgemm.cpp /tmp/cc7ghyo2.s: Assembler messages: /tmp/cc7ghyo2.s:31723: Error: no such instruction: `vpdpbssd -32(%r9),%ymm0,%ymm2' /tmp/cc7ghyo2.s:31863: Error: no such instruction: `vpdpbssd -32(%r9),%ymm0,%ymm1' /tmp/cc7ghyo2.s:31998: Error: no such instruction: `vpdpbssd 2(%r9,%rax),%ymm4,%ymm1' gmake[2]: *** [third_party/llama.cpp/CMakeFiles/ggml.dir/build.make:121: third_party/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o] Error 1 gmake[2]: *** Waiting for unfinished jobs.... gmake[2]: Leaving directory '/home/daodao/Develop/ktransformers/csrc/ktransformers_ext/build' gmake[1]: *** [CMakeFiles/Makefile2:264: third_party/llama.cpp/CMakeFiles/ggml.dir/all] Error 2 gmake[1]: *** Waiting for unfinished jobs.... [ 38%] Linking CXX static library libllamafile.a /usr/local/bin/cmake -P CMakeFiles/llamafile.dir/cmake_clean_target.cmake /usr/local/bin/cmake -E cmake_link_script CMakeFiles/llamafile.dir/link.txt --verbose=1``` ### Reproduction bash install.sh ### Environment CPU: Intel(R) Core(TM) Ultra 7 265K (without avx512 support) + RTX5080 CUDA12.8

bsakaguchi commented

2026-10-29 14:47:33 +00:00

Author

Owner

@zzningxp commented on GitHub (Nov 5, 2025):

Solved.
By alternating gcc-13 to gcc-11.

And this is caused by llama.cpp.

@zzningxp commented on GitHub (Nov 5, 2025): Solved. By alternating gcc-13 to gcc-11. And this is caused by llama.cpp.