ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 10:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert #79 (#192)

Browse Source 
* Revert "Do not quantize activations if not necessary (#79)"

This reverts commit 0bf4d99774.

* Fixed compilation after revert

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-02-08 09:48:59 +02:00
committed by GitHub
parent 4601a8c373
commit 6d7b58eade
2 changed files with 16 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/include/ggml.h
View File

@@ -724,7 +724,6 @@ extern "C" {
// since https://github.com/ggerganov/ggml/issues/287
struct ggml_cplan {
size_t work_size; // size of work buffer, calculated by `ggml_graph_plan()`
size_t q_size;
uint8_t * work_data; // work buffer, to be allocated by caller before calling to `ggml_graph_compute()`
int n_threads;