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 <redacted>
* musa: Remove workaround in PR #10042

Signed-off-by: Xiaodong Ye <redacted>
---------

Signed-off-by: Xiaodong Ye <redacted>

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index 6ea41577768c3ce9f7b904ab6d1e2292b675d06b..093ad70991b5a208f15db32c100ac91e1babfa04 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/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: