tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 13:05:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into gg/llama-kv-cache

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-18 10:14:37 +02:00
parent 1d801d27b9 73e2ed3ce3
commit f0d3ff2388
156 changed files with 6433 additions and 2603 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/imatrix/imatrix.cpp
View File

@ -3,6 +3,7 @@
#include "log.h"
#include "llama.h"
#include <chrono>
#include <cmath>
#include <cstdio>
#include <cstring>
@ -99,7 +100,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
const float * data = is_host ? (const float *) src1->data : m_src1_data.data();
// this has been adapted to the new format of storing merged experts in a single 3d tensor
// ref: https://github.com/ggerganov/llama.cpp/pull/6387
// ref: https://github.com/ggml-org/llama.cpp/pull/6387
if (t->op == GGML_OP_MUL_MAT_ID) {
// ids -> [n_experts_used, n_tokens]
// src1 -> [cols, n_expert_used, n_tokens]