CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add expert reduce kernel (#16857)

Browse Source 
* CUDA: add expert reduce kernel

* contigous checks, better formatting, use std::vector instead of array

* use vector empty instead of size

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Aman Gupta
2025-10-31 20:05:07 +08:00
committed by GitHub
parent 8da3c0e200
commit 4146d6a1a6
4 changed files with 263 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -27,6 +27,7 @@
#include "ggml-cuda/mmq.cuh"
#include "ggml-cuda/mmvf.cuh"
#include "ggml-cuda/mmvq.cuh"
#include "ggml-cuda/moe-expert-reduce.cuh"
#include "ggml-cuda/norm.cuh"
#include "ggml-cuda/opt-step-adamw.cuh"
#include "ggml-cuda/opt-step-sgd.cuh"
@@ -3169,6 +3170,31 @@ static void evaluate_and_capture_cuda_graph(ggml_backend_cuda_context * cuda_ctx
continue;
}
if (node->op == GGML_OP_MUL) {
int current_node = i + 1;
int num_views = 0;
int num_adds = 0;
while (current_node < cgraph->n_nodes && cgraph->nodes[current_node]->op == GGML_OP_VIEW) {
num_views++;
current_node++;
}
while (current_node < cgraph->n_nodes && cgraph->nodes[current_node]->op == GGML_OP_ADD &&
num_adds < num_views - 1) {
num_adds++;
current_node++;
}
if (num_adds == num_views - 1 && num_views > 0) {
ggml_tensor * dst_node = cgraph->nodes[current_node - 1];
if (ggml_cuda_should_use_moe_expert_reduce(cgraph, i, current_node)) {
ggml_cuda_op_moe_expert_reduce(*cuda_ctx, node->src[0], node->src[1], dst_node);
i += num_views + num_adds;
continue;
}
}
}
if (node->op == GGML_OP_ADD) {
int n_fuse = 0;
ggml_op ops[8];