CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-21 12:16:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

MUSA: support ARM64 and enable dp4a .etc (#11843)

Browse Source 
* MUSA:  support ARM64 and enable __dp4a .etc

* fix cross entropy loss op for musa

* update

* add cc info log for musa

* add comment for the MUSA .cc calculation block

---------

Co-authored-by: Bodhi Hu <huaishun.hu@mthreads.com>
This commit is contained in:
Bodhi
2025-02-21 15:46:23 +08:00
committed by GitHub
parent ee02ad02c5
commit 0b3863ff95
7 changed files with 25 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-cuda/cross-entropy-loss.cu
View File

@@ -123,13 +123,13 @@ void ggml_cuda_cross_entropy_loss(ggml_backend_cuda_context & ctx, ggml_tensor *
ggml_cuda_pool_alloc<float> dst_tmp(pool, blocks_num.x);
if (nbytes_shared <= smpbo) {
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) && !defined(GGML_USE_MUSA)
static bool shared_memory_limit_raised[GGML_CUDA_MAX_DEVICES] = {false};
if (!shared_memory_limit_raised[id]) {
CUDA_CHECK(cudaFuncSetAttribute(cross_entropy_loss_back_f32<true>, cudaFuncAttributeMaxDynamicSharedMemorySize, smpbo));
CUDA_CHECK(cudaFuncSetAttribute(cross_entropy_loss_f32<true>, cudaFuncAttributeMaxDynamicSharedMemorySize, smpbo));
shared_memory_limit_raised[id] = true;
}
#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) && !defined(GGML_USE_MUSA)
cross_entropy_loss_f32<true><<<blocks_num, blocks_dim, nbytes_shared, stream>>>(src0_d, src1_d, dst_tmp.ptr, ne00, nrows);
} else {
cross_entropy_loss_f32<false><<<blocks_num, blocks_dim, 0, stream>>>(src0_d, src1_d, dst_tmp.ptr, ne00, nrows);
@@ -175,13 +175,13 @@ void ggml_cuda_cross_entropy_loss_back(ggml_backend_cuda_context & ctx, ggml_ten
const size_t smpbo = ggml_cuda_info().devices[id].smpbo;
if (nbytes_shared <= smpbo) {
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) && !defined(GGML_USE_MUSA)
static bool shared_memory_limit_raised[GGML_CUDA_MAX_DEVICES] = {false};
if (!shared_memory_limit_raised[id]) {
CUDA_CHECK(cudaFuncSetAttribute(cross_entropy_loss_back_f32<true>, cudaFuncAttributeMaxDynamicSharedMemorySize, smpbo));
shared_memory_limit_raised[id] = true;
}
#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) && !defined(GGML_USE_MUSA)
cross_entropy_loss_back_f32<true><<<blocks_num, blocks_dim, nbytes_shared, stream>>>(grad_d, src0f_d, src1f_d, dst_d, ne00);
} else {
cross_entropy_loss_back_f32<false><<<blocks_num, blocks_dim, 0, stream>>>(grad_d, src0f_d, src1f_d, dst_d, ne00);