Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Revert "CUDA: add expert reduce kernel (#16857)" (#17100)

Browse Source
This commit is contained in:
Aman Gupta
2025-11-08 21:05:19 +08:00
committed by GitHub
parent c1b187688d
commit 64fe17fbb8
4 changed files with 0 additions and 263 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
-26
View File
@@ -27,7 +27,6 @@
#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"
@@ -3197,31 +3196,6 @@ 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];