vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : refactor rope norm/neox (#7634)

Browse source 
* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-06-05 11:29:20 +03:00 • committed by GitHub
parent 9973e81c5c
commit 2b3389677a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 485 additions and 732 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/test-grad0.cpp
View file

@ -1465,7 +1465,7 @@ int main(int argc, const char ** argv) {
continue;
}
struct ggml_tensor * f = ggml_sum(ctx0, ggml_rope(ctx0, x[0], p, n_rot, mode, 0));
struct ggml_tensor * f = ggml_sum(ctx0, ggml_rope(ctx0, x[0], p, n_rot, mode));
GGML_PRINT_DEBUG("rope f32: n_past: %d n_rot: %d mode: %d\n", n_past, n_rot, mode);
check_gradient("rope f32", ctx0, x, f, ndims, nargs, 1e-2f, 1e-3f, INFINITY);
@ -1505,7 +1505,7 @@ int main(int argc, const char ** argv) {
continue;
}
struct ggml_tensor * f = ggml_sum(ctx0, ggml_rope(ctx0, x[0], p, n_rot, mode, 0));
struct ggml_tensor * f = ggml_sum(ctx0, ggml_rope(ctx0, x[0], p, n_rot, mode));
GGML_PRINT_DEBUG("rope f16: n_past: %d n_rot: %d mode: %d\n", n_past, n_rot, mode);
check_gradient("rope f16", ctx0, x, f, ndims, nargs, 1e-1f, 1e-1f, INFINITY);