 Rickard Hallerbäck
|
dc6897404e
metal : reusing llama.cpp logging (#3152)
|
2 lat temu |
 Georgi Gerganov
|
8c00b7a6ff
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)
|
2 lat temu |
 slaren
|
15b67a66c2
llama-bench : use two tokens in the warmup run for prompt evals (#3059)
|
2 lat temu |
 Cebtenzzre
|
de2fe892af
examples : replace fprintf to stdout with printf (#3017)
|
2 lat temu |
|
Cebtenzzre
|
3103568144
llama-bench : make cpp file non-executable (#2999)
|
2 lat temu |
|
slaren
|
43033b7bb4
llama-bench : set locale to utf8 (#2832)
|
2 lat temu |
|
slaren
|
154725c543
llama-bench : add model sizes (#2771)
|
2 lat temu |
 Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
2 lat temu |
|
slaren
|
8e4364f2af
llama-bench : minor fixes (#2695)
|
2 lat temu |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 lat temu |
|
slaren
|
097e121e2f
llama : add benchmark example (#2626)
|
2 lat temu |
