Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
b1843
e7e4df03
·
llama : ggml-backend integration (#4766)
·
Jan 12, 2024
b1842
584d674b
·
llama : remove redundant assert for StableLM (#4901)
·
Jan 12, 2024
b1841
930f907d
·
export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894)
·
Jan 12, 2024
b1840
e790eef2
·
llama.swiftui : update models layout (#4826)
·
Jan 12, 2024
b1838
1b280c9f
·
CUDA: fix softmax compile for old CUDA versions (#4862)
·
Jan 12, 2024
b1837
3cabe806
·
llama : fix typo "imp_embd" -> "inp_embd"
·
Jan 12, 2024
b1836
4315a943
·
common : streamline the formatting of help (#4890)
·
Jan 12, 2024
b1834
f445c0e6
·
llama : fix llm_build_k_shift to use correct n_rot (#4889)
·
Jan 12, 2024
b1833
326b418b
·
Importance Matrix calculation (#4861)
·
Jan 12, 2024
b1832
1d118386
·
server : fix infill when prompt is empty (#4833)
·
Jan 11, 2024
b1831
7edefbd7
·
main : better name for variable n_print (#4874)
·
Jan 11, 2024
b1830
3ca63b45
·
main : disable token count by default (#4874)
·
Jan 11, 2024
b1829
b0377875
·
swift : track ggml release branch (#4867)
·
Jan 11, 2024
b1828
469e75d0
·
llama : restore intended k-quants mixes for MoE models (#4872)
·
Jan 11, 2024
b1827
49662cbe
·
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
·
Jan 11, 2024
b1826
3ba5b8ca
·
swift : pin ggml commit + remove ggml.h from spm-headers (#4878)
·
Jan 11, 2024
b1825
4330bd83
·
server : implement credentialed CORS (#4514)
·
Jan 11, 2024
b1824
27379455
·
server : support for multiple api keys (#4864)
·
Jan 11, 2024
b1823
eab67950
·
server : add `LOG_INFO` when model is successfully loaded (#4881)
·
Jan 11, 2024
b1822
d8d90aa3
·
ci: nix-flake-update: new token with pr permissions (#4879)
·
Jan 11, 2024
Prev
1
…
33
34
35
36
37
38
39
40
41
…
98
Next