 Daniel Bevenius
|
433def286e
llama : rename ctx to user_data in progress_callback (#7045)
|
1 år sedan |
 Bartowski
|
60325fa56f
Remove .attention from skipped tensors to match more accurately (#7051)
|
1 år sedan |
 alwqx
|
6ecf3189e0
chore: fix typo in llama.cpp (#7032)
|
1 år sedan |
 Andrew Downing
|
b0d943de17
Update LOG_IMPL and LOG_TEE_IMPL (#7029)
|
1 år sedan |
 l3utterfly
|
8d608a81b7
main : fix off by one error for context shift (#6921)
|
1 år sedan |
 Johannes Gäßler
|
3ea0d36000
Server: add tests for batch size, different seeds (#6950)
|
1 år sedan |
|
Johannes Gäßler
|
1613ef8d8e
CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
|
1 år sedan |
 slaren
|
c4ec9c0d3d
ci : exempt confirmed bugs from being tagged as stale (#7014)
|
1 år sedan |
|
Johannes Gäßler
|
a8f9b07631
perplexity: more statistics, added documentation (#6936)
|
1 år sedan |
 Kevin Gibbons
|
f364eb6fb5
switch to using localizedDescription (#7010)
|
1 år sedan |
 Georgi Gerganov
|
77e15bec62
metal : remove deprecated error code (#7008)
|
1 år sedan |
|
Kevin Gibbons
|
a68a1e7ed0
metal : log more info on error (#6987)
|
1 år sedan |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 år sedan |
|
Georgi Gerganov
|
952d03dbea
convert : use utf8 encoding (#7000)
|
1 år sedan |
 Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
1 år sedan |
 Clint Herron
|
b8c1476e44
Extending grammar integration tests (#6644)
|
1 år sedan |
|
Daniel Bevenius
|
5539e6fdd1
main : fix typo in comment in main.cpp (#6985)
|
1 år sedan |
|
Olivier Chafik
|
b8a7a5a90f
build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
|
1 år sedan |
|
Georgi Gerganov
|
d2c898f746
ci : tmp disable gguf-split (#6983)
|
1 år sedan |
|
Georgi Gerganov
|
544f1f10ad
ggml : fix __MSC_VER -> _MSC_VER (#6977)
|
1 år sedan |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
1 år sedan |
|
Georgi Gerganov
|
24affa7db3
readme : update hot topics
|
1 år sedan |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 år sedan |
 David Renshaw
|
3f167476b1
sampling : use std::random_device{}() for default random seed (#6962)
|
1 år sedan |
 Christian Zhou-Zheng
|
3055a41805
convert : fix conversion of some BERT embedding models (#6937)
|
1 år sedan |
 Przemysław Pawełczyk
|
577277ffd2
make : change GNU make default CXX from g++ to c++ (#6966)
|
1 år sedan |
|
Przemysław Pawełczyk
|
ca7f29f568
ci : add building in MSYS2 environments (Windows) (#6967)
|
1 år sedan |
|
Johannes Gäßler
|
c4f708a93f
llama : fix typo LAMMAFILE -> LLAMAFILE (#6974)
|
1 år sedan |
 DAN™
|
e00b4a8f81
Fix more int overflow during quant (PPL/CUDA). (#6563)
|
1 år sedan |
 Xuan Son Nguyen
|
7bb36ccf91
gguf : enforce that tensor names are unique (#6905)
|
1 år sedan |
