 Olivier Chafik
|
b8a7a5a90f
build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
|
1 year ago |
 Georgi Gerganov
|
d2c898f746
ci : tmp disable gguf-split (#6983)
|
1 year ago |
|
Georgi Gerganov
|
544f1f10ad
ggml : fix __MSC_VER -> _MSC_VER (#6977)
|
1 year ago |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
1 year ago |
|
Georgi Gerganov
|
24affa7db3
readme : update hot topics
|
1 year ago |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 year ago |
 David Renshaw
|
3f167476b1
sampling : use std::random_device{}() for default random seed (#6962)
|
1 year ago |
 Christian Zhou-Zheng
|
3055a41805
convert : fix conversion of some BERT embedding models (#6937)
|
1 year ago |
 Przemysław Pawełczyk
|
577277ffd2
make : change GNU make default CXX from g++ to c++ (#6966)
|
1 year ago |
|
Przemysław Pawełczyk
|
ca7f29f568
ci : add building in MSYS2 environments (Windows) (#6967)
|
1 year ago |
 Johannes Gäßler
|
c4f708a93f
llama : fix typo LAMMAFILE -> LLAMAFILE (#6974)
|
1 year ago |
 DAN™
|
e00b4a8f81
Fix more int overflow during quant (PPL/CUDA). (#6563)
|
1 year ago |
 Xuan Son Nguyen
|
7bb36ccf91
gguf : enforce that tensor names are unique (#6905)
|
1 year ago |
 Neo Zhang
|
ce023f6f2f
add device version in device list (#6959)
|
1 year ago |
 github-actions[bot]
|
6e472f58e4
flake.lock: Update
|
1 year ago |
 mgroeber9110
|
4dba7e8114
Replace "alternative" boolean operator in conditional compilation directive (#6949)
|
1 year ago |
 Pierrick Hymbert
|
b7368332e2
ci: server: tests python env on github container ubuntu latest / fix n_predict (#6935)
|
1 year ago |
 agray3
|
928e0b7013
Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
|
1 year ago |
|
Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
1 year ago |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
1 year ago |
|
slaren
|
e2764cd7ca
gguf : fix mismatch between alloc and free functions (#6929)
|
1 year ago |
 Justine Tunney
|
4b1c3c98b4
llamafile : use 64-bit integers in sgemm (#6928)
|
1 year ago |
|
Pierrick Hymbert
|
bbe3c6e761
ci: server: fix python installation (#6925)
|
1 year ago |
|
Pierrick Hymbert
|
7f5ff558ee
server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
|
1 year ago |
|
Pierrick Hymbert
|
9e4e077ec5
ci: server: fix python installation (#6922)
|
1 year ago |
|
Georgi Gerganov
|
83b72cb086
Merge pull request from GHSA-p5mv-gjc5-mwqv
|
1 year ago |
|
Pierrick Hymbert
|
d4a9afc100
ci: server: fix python installation (#6918)
|
1 year ago |
|
Pierrick Hymbert
|
7d641c26ac
ci: fix concurrency for pull_request_target (#6917)
|
1 year ago |
|
Pierrick Hymbert
|
5790c8dac1
bench: server add stop word for PHI-2 (#6916)
|
1 year ago |
 vik
|
46e12c4692
llava : add support for moondream vision language model (#6899)
|
1 year ago |
