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

2
kompute-shaders/op_rope_f16.comp
View file

@ -14,7 +14,7 @@ void main() {
const bool is_neox = (pcs.mode & 2) != 0;
float corr_dims[2];
rope_yarn_corr_dims(pcs.n_dims, pcs.n_orig_ctx, pcs.freq_base, pcs.beta_fast, pcs.beta_slow, corr_dims);
rope_yarn_corr_dims(pcs.n_dims, pcs.n_ctx_orig, pcs.freq_base, pcs.beta_fast, pcs.beta_slow, corr_dims);
const float theta_scale = pow(pcs.freq_base, -2.0/pcs.n_dims);

2
kompute-shaders/op_rope_f32.comp
View file

@ -14,7 +14,7 @@ void main() {
const bool is_neox = (pcs.mode & 2) != 0;
float corr_dims[2];
rope_yarn_corr_dims(pcs.n_dims, pcs.n_orig_ctx, pcs.freq_base, pcs.beta_fast, pcs.beta_slow, corr_dims);
rope_yarn_corr_dims(pcs.n_dims, pcs.n_ctx_orig, pcs.freq_base, pcs.beta_fast, pcs.beta_slow, corr_dims);
const float theta_scale = pow(pcs.freq_base, -2.0/pcs.n_dims);

12
kompute-shaders/rope_common.comp
View file

@ -9,7 +9,7 @@ layout (push_constant) uniform parameter {
uint outOff;
int n_dims;
int mode;
int n_orig_ctx;
int n_ctx_orig;
float freq_base;
float freq_scale;
float ext_factor;
@ -54,14 +54,14 @@ void rope_yarn(
// Apparently solving `n_rot = 2pi * x * base^((2 * max_pos_emb) / n_dims)` for x, we get
// `corr_fac(n_rot) = n_dims * log(max_pos_emb / (n_rot * 2pi)) / (2 * log(base))`
float rope_yarn_corr_factor(int n_dims, int n_orig_ctx, float n_rot, float base) {
return n_dims * log(n_orig_ctx / (n_rot * TWOPI_F)) / (2 * log(base));
float rope_yarn_corr_factor(int n_dims, int n_ctx_orig, float n_rot, float base) {
return n_dims * log(n_ctx_orig / (n_rot * TWOPI_F)) / (2 * log(base));
}
void rope_yarn_corr_dims(
int n_dims, int n_orig_ctx, float freq_base, float beta_fast, float beta_slow, out float dims[2]
int n_dims, int n_ctx_orig, float freq_base, float beta_fast, float beta_slow, out float dims[2]
) {
// start and end correction dims
dims[0] = max(0.0f, floor(rope_yarn_corr_factor(n_dims, n_orig_ctx, beta_fast, freq_base)));
dims[1] = min(n_dims - 1.0f, ceil(rope_yarn_corr_factor(n_dims, n_orig_ctx, beta_slow, freq_base)));
dims[0] = max(0.0f, floor(rope_yarn_corr_factor(n_dims, n_ctx_orig, beta_fast, freq_base)));
dims[1] = min(n_dims - 1.0f, ceil(rope_yarn_corr_factor(n_dims, n_ctx_orig, beta_slow, freq_base)));
}