CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix rope with partial rotation and non-cont src (#14580)

Browse Source 
* cuda : fix rope non-cont

ggml-ci

* cont : fix multi-rope + add test

ggml-ci

* sycl : try fix

ggml-ci

* cont : fix sycl + clean-up cuda

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-08 10:15:21 +03:00
committed by GitHub
parent 75c91de6e9
commit 4d0dcd4a06
3 changed files with 50 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
ggml/src/ggml-cuda/rope.cu
View File

@@ -50,21 +50,19 @@ static __global__ void rope_norm(
const int row_dst = blockDim.x*blockIdx.x + threadIdx.x;
if (i0 >= n_dims) {
const int i = row_dst*ne0 + i0;
dst[i + 0] = x[i + 0];
dst[i + 1] = x[i + 1];
return;
}
const int row_x = row_dst % ne1;
const int channel_x = row_dst / ne1;
const int idst = row_dst*ne0 + i0;
const int ix = channel_x*s2 + row_x*s1 + i0;
if (i0 >= n_dims) {
dst[idst + 0] = x[ix + 0];
dst[idst + 1] = x[ix + 1];
return;
}
const float theta_base = pos[channel_x]*powf(theta_scale, i0/2.0f);
const float freq_factor = has_ff ? freq_factors[i0/2] : 1.0f;
@@ -94,21 +92,19 @@ static __global__ void rope_neox(
const int row_dst = blockDim.x*blockIdx.x + threadIdx.x;
if (i0 >= n_dims) {
const int i = row_dst*ne0 + i0;
dst[i + 0] = x[i + 0];
dst[i + 1] = x[i + 1];
return;
}
const int row_x = row_dst % ne1;
const int channel_x = row_dst / ne1;
const int idst = row_dst*ne0 + i0/2;
const int ix = channel_x*s2 + row_x*s1 + i0/2;
if (i0 >= n_dims) {
dst[idst + i0/2 + 0] = x[ix + i0/2 + 0];
dst[idst + i0/2 + 1] = x[ix + i0/2 + 1];
return;
}
const float theta_base = pos[channel_x]*powf(theta_scale, i0/2.0f);
const float freq_factor = has_ff ? freq_factors[i0/2] : 1.0f;
@@ -138,21 +134,19 @@ static __global__ void rope_multi(
const int row_dst = blockDim.x*blockIdx.x + threadIdx.x;
if (i0 >= n_dims) {
const int i = row_dst*ne0 + i0;
dst[i + 0] = x[i + 0];
dst[i + 1] = x[i + 1];
return;
}
const int row_x = row_dst % ne1;
const int channel_x = row_dst / ne1;
const int idst = row_dst*ne0 + i0/2;
const int ix = channel_x*s2 + row_x*s1 + i0/2;
if (i0 >= n_dims) {
dst[idst + i0/2 + 0] = x[ix + i0/2 + 0];
dst[idst + i0/2 + 1] = x[ix + i0/2 + 1];
return;
}
const int sect_dims = sections.v[0] + sections.v[1] + sections.v[2] + sections.v[3];
const int sec_w = sections.v[1] + sections.v[0];
const int sector = (i0 / 2) % sect_dims;