public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml: fix CUDA grid launch condition for large block_nums.y in binbcast (llama/16742) 

* Fix CUDA grid launch condition for large block_nums.y

* add backend ops test

* reduce test  repetitions
This commit is contained in:
leejet 2025-10-25 03:39:37 +08:00 committed by Georgi Gerganov
parent 524046d4d1
commit 5166efa7f0
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/binbcast.cu
View File

@ -272,7 +272,7 @@ static void launch_bin_bcast_pack(const ggml_tensor * src0, const ggml_tensor *
const uint3 ne12 = init_fastdiv_values((uint32_t) cne1[2]); const uint3 ne12 = init_fastdiv_values((uint32_t) cne1[2]);
const uint3 ne13 = init_fastdiv_values((uint32_t) cne1[3]); const uint3 ne13 = init_fastdiv_values((uint32_t) cne1[3]);
if (block_nums.z > 65535) { if (block_nums.z > 65535 || block_nums.y > 65535) {
int block_num = (ne0 * ne1 * ne2 * ne3 + block_size - 1) / block_size; int block_num = (ne0 * ne1 * ne2 * ne3 + block_size - 1) / block_size;
const uint3 prod_012 = init_fastdiv_values((uint32_t) (ne0 * ne1 * ne2)); const uint3 prod_012 = init_fastdiv_values((uint32_t) (ne0 * ne1 * ne2));
const uint3 prod_01 = init_fastdiv_values((uint32_t) (ne0 * ne1)); const uint3 prod_01 = init_fastdiv_values((uint32_t) (ne0 * ne1));