nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 36 Packages Projects Releases Wiki Activity

Deduplicate q4 quantization functions (#383)

Browse Source 
* Deduplicate q4 quantization functions

* Use const; add basic test

* Re-enable quantization test

* Disable AVX2 flags in CI

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter
2023-03-22 19:29:06 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent 97940520e8
commit 69c92298a9
5 changed files with 119 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml.h
+2 -2
View File
@@ -745,8 +745,8 @@ enum ggml_opt_result ggml_opt(
// quantization
//
size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t * hist);
size_t ggml_quantize_q4_1(float * src, void * dst, int n, int k, int qk, int64_t * hist);
size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int qk, int64_t * hist);
size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int qk, int64_t * hist);
//
// system info