You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Intel MKL ERROR: Parameter 8 was incorrect on entry to SGEMM
Intel MKL ERROR: Parameter 13 was incorrect on entry to SGEMM
What we've tried:
Set LD_PRELOAD=/usr/local/libfakeintel.so (fake Intel library is present)
Set MKL_DEBUG_CPU_TYPE=5 (force AVX2)
Reduced batch sizes and concurrency
ONNX version has different compatibility issues
Root Cause:
The SGEMM errors indicate incorrect matrix dimensions/parameters being passed to Intel MKL BLAS routines. This appears to be a bug in the Candle backend's Qwen3 CPU implementation when compiled with Intel MKL, not just an AMD CPU detection issue.
Potential Solutions:
Use a TEI build compiled with OpenBLAS instead of Intel MKL
Fix the matrix dimension bug in the Candle backend code
Use a working custom image without MKL dependencies