Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[User] Can't build for a CPU without AVX/AVX2 #1532

Closed
alk0 opened this issue May 20, 2023 · 1 comment
Closed

[User] Can't build for a CPU without AVX/AVX2 #1532

alk0 opened this issue May 20, 2023 · 1 comment

Comments

@alk0
Copy link

alk0 commented May 20, 2023

Can't build for a CPU without AVX/AVX2, most probably after 2d5db48
Environment: Linux, Arch, AMD Athlon 64 X2 (please stop laughing), make LLAMA_OPENBLAS=1 (doesn't matter).

ggml.c: In function ‘ggml_vec_dot_q4_1_q8_1’:
ggml.c:2484:37: error: incompatible type for argument 1 of ‘ggml_lookup_fp16_to_fp32’
 2484 |         sumf += (GGML_FP16_TO_FP32(x[i]).d*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
      |                                    ~^~~
      |                                     |
      |                                     block_q4_1
ggml.c:358:55: note: in definition of macro ‘GGML_FP16_TO_FP32’
  358 | #define GGML_FP16_TO_FP32(x) ggml_lookup_fp16_to_fp32(x)
      |                                                       ^
ggml.c:352:58: note: expected ‘ggml_fp16_t’ {aka ‘short unsigned int’} but argument is of type ‘block_q4_1’
  352 | inline static float ggml_lookup_fp16_to_fp32(ggml_fp16_t f) {
      |                                              ~~~~~~~~~~~~^
make: *** [Makefile:186: ggml.o] Error 1
@ggerganov
Copy link
Member

Fixed with 4fd3e29

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants