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

CUDA: General GEMV fusion (#16715)

Browse Source
This commit is contained in:
Aman Gupta
2025-10-26 19:28:04 +08:00
committed by GitHub
parent 3cfa9c3f12
commit f77c13b91f
11 changed files with 1096 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmvq.cuh
+1 -1
View File
@@ -3,7 +3,7 @@
#define MMVQ_MAX_BATCH_SIZE 8 // Max. batch size for which to use MMVQ kernels.
void ggml_cuda_mul_mat_vec_q(ggml_backend_cuda_context & ctx,
const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst);
const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst, const ggml_cuda_mm_fusion_args_host * fusion = nullptr);
void ggml_cuda_op_mul_mat_vec_q(
ggml_backend_cuda_context & ctx,