mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 Packages Projects Releases Wiki Activity

sycl: fix norm kernels: l2_norm, group_norm, rms_norm by remove assert to support more cases (#19154)

Browse Source 
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
This commit is contained in:
Neo Zhang
2026-01-29 09:20:22 +08:00
committed by GitHub
parent 50e8962f79
commit d4964a7c66
3 changed files with 753 additions and 600 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/norm.cpp
-3
View File
@@ -251,7 +251,6 @@ static void norm_f32_sycl(const float * x, float * dst, const int ncols, const i
const float eps, queue_ptr stream, int device) {
const sycl::range<3> global_dims(nsamples, nchannels, nrows);
GGML_ASSERT(ncols % WARP_SIZE == 0);
if (ncols < 1024) {
const sycl::range<3> block_dims(1, 1, WARP_SIZE);
stream->submit([&](sycl::handler& cgh) {
@@ -334,7 +333,6 @@ static void group_norm_f32_sycl(const float* x, float* dst,
static void rms_norm_f32_sycl(const float* x, float* dst, const int ncols, const int nrows, const int nchannels, const int nsamples,
const int64_t stride_row, const int64_t stride_channel, const int64_t stride_sample, const float eps, queue_ptr stream, int device) {
GGML_ASSERT(ncols % WARP_SIZE == 0);
// printf("%s ncols=%d, nrows=%d, WARP_SIZE=%d\n", __func__, ncols, nrows, WARP_SIZE);
const sycl::range<3> global_dims(nsamples, nchannels, nrows);
@@ -374,7 +372,6 @@ static void rms_norm_f32_sycl(const float* x, float* dst, const int ncols, const
static void l2_norm_f32_sycl(const float* x, float* dst, const int ncols,
const int nrows, const float eps,
queue_ptr stream, int device) {
GGML_ASSERT(ncols % WARP_SIZE == 0);
// printf("%s ncols=%d, nrows=%d, WARP_SIZE=%d\n", __func__, ncols, nrows, WARP_SIZE);
if (ncols < 1024) {
const sycl::range<3> block_dims(1, 1, WARP_SIZE);