ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-02-28 19:25:56 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

musa: bump MUSA SDK version to rc3.1.1 (llama/11822)

Browse Source 
* musa: Update MUSA SDK version to rc3.1.1

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: Remove workaround in PR #10042

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2025-02-13 20:28:18 +08:00 committed by Georgi Gerganov
parent d2c5154bb5
commit 4e07957bf9
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@ -1480,12 +1480,7 @@ static void ggml_cuda_op_mul_mat(
const size_t nbytes_data = ggml_nbytes(src0);
const size_t nbytes_padding = ggml_row_size(src0->type, MATRIX_ROW_PADDING - ne00 % MATRIX_ROW_PADDING);
dev[id].src0_dd = dev[id].src0_dd_alloc.alloc(ctx.pool(id), nbytes_data + nbytes_padding);
// TODO: remove this for MUSA once the Guilty Lockup issue is resolved
#ifndef GGML_USE_MUSA
CUDA_CHECK(cudaMemsetAsync(dev[id].src0_dd, 0, nbytes_data + nbytes_padding, stream));
#else // GGML_USE_MUSA
CUDA_CHECK(cudaMemsetAsync(dev[id].src0_dd + nbytes_data, 0, nbytes_padding, stream));
#endif // !GGML_USE_MUSA
}
// If src0 is on a temporary compute buffer (partial offloading) there may be some padding that needs to be cleared: