 Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
c3ac702e5e
ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dst
|
%!s(int64=2) %!d(string=hai) anos |
 comex
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
%!s(int64=2) %!d(string=hai) anos |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
986b6ce9f9
ggml, llama : avoid heavy V transpose + improvements (#775)
|
%!s(int64=2) %!d(string=hai) anos |
 Marian Cepok
|
c0bb1d3ce2
ggml : change ne to int64_t (#626)
|
%!s(int64=2) %!d(string=hai) anos |
 Justine Tunney
|
6f23ba5ee2
Ensure --mlock works properly with mmap() support
|
%!s(int64=2) %!d(string=hai) anos |
 Slaren
|
c03ae8dca1
Add mmap support for model files
|
%!s(int64=2) %!d(string=hai) anos |
|
Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
%!s(int64=2) %!d(string=hai) anos |
|
comex
|
563cdc391d
Support calling mlock() on loaded model data on Linux and macOS (#453)
|
%!s(int64=2) %!d(string=hai) anos |
|
Stephan Walter
|
69c92298a9
Deduplicate q4 quantization functions (#383)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
f5a77a629b
Introduce C-style API (#370)
|
%!s(int64=2) %!d(string=hai) anos |
 hoangmit
|
6eac39ba95
Add RMS norm and use it (#187)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
26c0846629
Initial release
|
%!s(int64=2) %!d(string=hai) anos |
