From: R0CKSTAR Date: Thu, 13 Feb 2025 12:28:18 +0000 (+0800) Subject: musa: bump MUSA SDK version to rc3.1.1 (llama/11822) X-Git-Tag: upstream/0.0.1802~76 X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=28f5b6c410b123c293497d1ad0155d7b6b4c0698;p=pkg%2Fggml%2Fsources%2Fggml musa: bump MUSA SDK version to rc3.1.1 (llama/11822) * musa: Update MUSA SDK version to rc3.1.1 Signed-off-by: Xiaodong Ye * musa: Remove workaround in PR #10042 Signed-off-by: Xiaodong Ye --------- Signed-off-by: Xiaodong Ye --- diff --git a/src/ggml-cuda/ggml-cuda.cu b/src/ggml-cuda/ggml-cuda.cu index 6ea41577..093ad709 100644 --- a/src/ggml-cuda/ggml-cuda.cu +++ b/src/ggml-cuda/ggml-cuda.cu @@ -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: