CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

cann: support q4_0 model (#8822)

Browse Source
This commit is contained in:
wangshuai09
2024-08-05 12:22:30 +08:00
committed by GitHub
parent 0d6fb52be0
commit c02b0a8a4d
7 changed files with 357 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cann/kernels/ascendc_kernels.h
View File

@@ -8,6 +8,8 @@
#include "aclrtlaunch_ascendc_quantize_f32_q8_0.h"
#include "aclrtlaunch_ascendc_quantize_f16_q8_0.h"
#include "aclrtlaunch_ascendc_quantize_f16_to_q4_0.h"
#include "aclrtlaunch_ascendc_quantize_f32_to_q4_0.h"
#include "aclrtlaunch_ascendc_dup_by_rows_fp16.h"
#include "aclrtlaunch_ascendc_dup_by_rows_fp32.h"