root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

imatrix : remove invalid assert (#6632)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-04-12 11:49:58 +03:00 committed by GitHub
parent dee7f8d692
commit ef21ce4ccb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/imatrix/imatrix.cpp
View File

@ -107,9 +107,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
// the top-k selected expert ids are stored in the ids tensor // the top-k selected expert ids are stored in the ids tensor
// for simplicity, always copy ids to host, because it is small // for simplicity, always copy ids to host, because it is small
// take into account that ids is not contiguous!
GGML_ASSERT(ids->ne[1] == src1->ne[1]); GGML_ASSERT(ids->ne[1] == src1->ne[1]);
GGML_ASSERT(n_as*ggml_nrows(ids)*sizeof(int) == GGML_PAD(ggml_nbytes(ids), n_as*sizeof(int)));
m_ids.resize(ggml_nbytes(ids)/sizeof(int)); m_ids.resize(ggml_nbytes(ids)/sizeof(int));
ggml_backend_tensor_get(ids, m_ids.data(), 0, ggml_nbytes(ids)); ggml_backend_tensor_get(ids, m_ids.data(), 0, ggml_nbytes(ids));