Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 19, 2024
.
llama-bench-fixes
5bc418fa
·
llama-bench : minor fixes
·
Aug 22, 2023
gguf
66a66a05
·
readme : add notice about new file format
·
Aug 21, 2023
cuda-graph-allocr
0fc72f31
·
cleanup
·
Aug 21, 2023
ik/hellaswag-2
c9d9b052
·
HellaSwag: split token evaluation into batches if needed
·
Aug 20, 2023
ik/hellaswag
05ef02ae
·
More efficient Hellaswag implementation
·
Aug 20, 2023
ggml-type-traits
946e3138
·
ggml : move all type info to ggml_type_traits
·
Aug 19, 2023
lora-ci
e9b504dd
·
add test with q8_0 (cpu only)
·
Aug 18, 2023
server-default
3b436847
·
server : better default prompt
·
Aug 17, 2023
llama-benchmark
df87dd74
·
formatting
·
Aug 17, 2023
gguf-write-single-pass
6a9e6375
·
gguf.py : indentation
·
Aug 17, 2023
gguf-convert
5d044403
·
Merge branch 'gguf' into gguf-convert
·
Aug 17, 2023
server-ignore-hpp-asset
d8e03ed8
·
server : attempt use valid xxd command on linux
·
Aug 17, 2023
gguf-deduplicate
795ec707
·
examples : dedup simple
·
Aug 16, 2023
gguf-quant-tensor-names
29743cb8
·
gguf : define tensor names as constants
·
Aug 15, 2023
gguf-refactor-loading
2e07b995
·
wip
·
Aug 15, 2023
gguf-sync
f8539525
·
llama : refactor gguf_buffer and gguf_ctx_buffer
·
Aug 14, 2023
zig-fixes
84f7995e
·
Change LTO to option and other stuff
·
Aug 09, 2023
server-cfg
28046d1e
·
Merge and update
·
Aug 09, 2023
fix-params
dd50b77d
·
ggml : fix params pointer
·
Aug 07, 2023
k-view3d
5ddfbffb
·
llama : replace (permute + reshape + view_1d) with (view_3d)
·
Aug 07, 2023
Prev
1
…
18
19
20
21
22
23
24
25
26
Next