Replies: 1 comment
-
How to use CUDA or OpenCL without AVX2? - koboldcpp |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
When trying to run the main.exe binaries from
llama-b1621-bin-win-cublas-cu11.7.1-x64.zip
always gets an error
I checked both under windows 10 and 11 and gets the same error.
My CPU does not support AVX2 - Xeon(R) CPU E5-1650 v2 @ 3.50GHz
system_info: n_threads = 10 / 12 | AVX = 1 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
Is it because of the CPU it receives this error ?
The binaries for AVX1 work for me without any problem.
In that case, do I have to make my own compilation for CUBLAS and AVX1 ?
I have not been able to find any information on this subject
Beta Was this translation helpful? Give feedback.
All reactions