bradmit

Multi Threaded issue with CUDA compiled library 1.5.4

10

I've recently compiled the 1.5.4 library for with CUBLAS and having an issue where running multiple whisper_full_with_state()'s. I did not previously have this issue with the 1.5.1 library. I re-compiled...

Seems to be the same issue at: https://github.com/ggerganov/llama.cpp/issues/4208 I CC: clang version 17.0.6 (Red Hat 17.0.6-1.0.1.module+el8.10.0+90260+0be6147c) I CXX: gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-22.0.1) I NVCC: Build cuda_12.2.r12.2/compiler.33191640_0 !!!...