 Przemysław Pawełczyk
|
ca7f29f568
ci : add building in MSYS2 environments (Windows) (#6967)
|
hai 1 ano |
 Johannes Gäßler
|
c4f708a93f
llama : fix typo LAMMAFILE -> LLAMAFILE (#6974)
|
hai 1 ano |
 DAN™
|
e00b4a8f81
Fix more int overflow during quant (PPL/CUDA). (#6563)
|
hai 1 ano |
 Xuan Son Nguyen
|
7bb36ccf91
gguf : enforce that tensor names are unique (#6905)
|
hai 1 ano |
 Neo Zhang
|
ce023f6f2f
add device version in device list (#6959)
|
hai 1 ano |
 github-actions[bot]
|
6e472f58e4
flake.lock: Update
|
hai 1 ano |
 mgroeber9110
|
4dba7e8114
Replace "alternative" boolean operator in conditional compilation directive (#6949)
|
hai 1 ano |
 Pierrick Hymbert
|
b7368332e2
ci: server: tests python env on github container ubuntu latest / fix n_predict (#6935)
|
hai 1 ano |
 agray3
|
928e0b7013
Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
|
hai 1 ano |
|
Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
hai 1 ano |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
hai 1 ano |
|
slaren
|
e2764cd7ca
gguf : fix mismatch between alloc and free functions (#6929)
|
hai 1 ano |
 Justine Tunney
|
4b1c3c98b4
llamafile : use 64-bit integers in sgemm (#6928)
|
hai 1 ano |
|
Pierrick Hymbert
|
bbe3c6e761
ci: server: fix python installation (#6925)
|
hai 1 ano |
|
Pierrick Hymbert
|
7f5ff558ee
server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
|
hai 1 ano |
|
Pierrick Hymbert
|
9e4e077ec5
ci: server: fix python installation (#6922)
|
hai 1 ano |
 Georgi Gerganov
|
83b72cb086
Merge pull request from GHSA-p5mv-gjc5-mwqv
|
hai 1 ano |
|
Pierrick Hymbert
|
d4a9afc100
ci: server: fix python installation (#6918)
|
hai 1 ano |
|
Pierrick Hymbert
|
7d641c26ac
ci: fix concurrency for pull_request_target (#6917)
|
hai 1 ano |
|
Pierrick Hymbert
|
5790c8dac1
bench: server add stop word for PHI-2 (#6916)
|
hai 1 ano |
 vik
|
46e12c4692
llava : add support for moondream vision language model (#6899)
|
hai 1 ano |
|
Georgi Gerganov
|
dba497e0c1
cmake : restore LLAMA_LLAMAFILE_DEFAULT
|
hai 1 ano |
|
Georgi Gerganov
|
fa0b4ad252
cmake : remove obsolete ANDROID check
|
hai 1 ano |
|
slaren
|
d6e1d44f16
llama : synchronize before get/set session data (#6911)
|
hai 1 ano |
|
Georgi Gerganov
|
853d06ffe2
ci : tmp disable slow tests
|
hai 1 ano |
 BarfingLemurs
|
3fe0596c18
readme : update model list (#6908)
|
hai 1 ano |
|
slaren
|
0ead1f1072
llama : check that all the tensor data is in the model file (#6885)
|
hai 1 ano |
|
Georgi Gerganov
|
51543729ff
ggml : fix redefinition of vaddvq_f32 for 32-bit ARM (#6906)
|
hai 1 ano |
 Daniel Bevenius
|
4ab99d8d47
clip : rename lerp function to avoid conflict (#6894)
|
hai 1 ano |
|
Georgi Gerganov
|
54770413c4
ggml : fix MIN / MAX macros (#6904)
|
hai 1 ano |
