Tags
Tags give the ability to mark specific points in history as being important
master-9cbc404
9cbc404b
·
ci : re-enable AVX512 testing (Windows-MSVC) (#584)
·
Mar 29, 2023
master-b51c717
b51c717d
·
ggml : init time on first ggml_init() call
·
Mar 29, 2023
master-0ba76c1
0ba76c1e
·
llama : fix compile warnings when reading the vocab
·
Mar 29, 2023
master-cea1c85
cea1c859
·
ggml : add ARM_NEON dequantize_row_q4_1()
·
Mar 29, 2023
master-f202ada
f202ada1
·
ggml : add ARM_NEON quantize_row_q4_1()
·
Mar 29, 2023
master-83df563
83df5639
·
Fix GCC warning about binary literal (#595)
·
Mar 29, 2023
master-a5c42c4
a5c42c4b
·
Fix typo in llama.h (#593)
·
Mar 29, 2023
master-5a5f8b1
5a5f8b15
·
Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector extensions on MSVC (#375)
·
Mar 28, 2023
master-f121705
f1217055
·
CI: fix subdirectory path globbing (#546)
·
Mar 28, 2023
master-7f4c5c6
7f4c5c66
·
llama : fix linkage with mingw (#551)
·
Mar 28, 2023
master-2a98bc1
2a98bc18
·
ggml : add AVX2 implementation of quantize_row_q4_1 (#515)
·
Mar 28, 2023
master-d0aaff5
d0aaff57
·
py : add temporary script to convert old ggml files to newer version (#539)
·
Mar 28, 2023
master-99c5b27
99c5b276
·
ggml : refactor quantized processing functions (#509)
·
Mar 28, 2023
master-96f9c05
96f9c050
·
ci : make ctest verbose, hopefully we see what is wrong with the sanitizer
·
Mar 28, 2023
master-d502bc7
d502bc7c
·
tests : free llama context at the end of the test
·
Mar 28, 2023
master-436e561
436e5619
·
all : be more strict about converting float to double (#458)
·
Mar 28, 2023
master-20e1e84
20e1e848
·
deploy : add a Package.swift for SwiftPM support (#393)
·
Mar 28, 2023
master-c1f8850
c1f88506
·
ggml : introduce structs for the q4 data blocks (#356)
·
Mar 28, 2023
master-a6bdc47
a6bdc47c
·
Fix usage of F16C intrinsics in AVX code (#563)
·
Mar 28, 2023
master-7b8dbcb
7b8dbcb7
·
main.cpp fixes, refactoring (#571)
·
Mar 28, 2023
1
…
30
31
32
33
34
35
36
37
38