 Georgi Gerganov
|
68a6b98b3c
make : fix CUDA build (#5580)
|
1 year ago |
 valiray
|
70d45af0ef
readme : fix typo in README-sycl.md (#5353)
|
1 year ago |
 Abhilash Majumder
|
13e2c771aa
cmake : remove obsolete sycl compile flags (#5581)
|
1 year ago |
|
Georgi Gerganov
|
f53119cec4
minor : fix trailing whitespace (#5538)
|
1 year ago |
 Daniel Bevenius
|
7084755396
llava : avoid changing the original BakLLaVA model (#5577)
|
1 year ago |
 NawafAlansari
|
4480542b22
baby-llama : allocate graphs in ggml_context (#5573)
|
1 year ago |
 Xuan Son Nguyen
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
1 year ago |
 slaren
|
3a9cb4ca64
cuda, metal : fix nans in soft_max (#5574)
|
1 year ago |
 Mirko185
|
769a716e30
readme : update (#5572)
|
1 year ago |
 bmwl
|
f0d1fafc02
ggml : android and old glibc NUMA incompatibility bugfixes (#5557)
|
1 year ago |
 Jared Van Bortel
|
a0c2dad9d4
build : pass all warning flags to nvcc via -Xcompiler (#5570)
|
1 year ago |
|
Georgi Gerganov
|
14278f55d2
ggml : restore vec dot stride arg names (#5453)
|
1 year ago |
|
Georgi Gerganov
|
b1de96824b
ci : fix wikitext url + compile warnings (#5569)
|
1 year ago |
|
Georgi Gerganov
|
7ad554f90e
metal : fix unused warnings (#0)
|
1 year ago |
 Robey Holderith
|
5ee99c32f5
common, server : surface min_keep as its own parameter (#5567)
|
1 year ago |
 Pierrick Hymbert
|
c145f8a132
server : slots monitoring endpoint (#5550)
|
1 year ago |
|
Georgi Gerganov
|
689a091bbe
sampling : do not set min_keep to n_probs (#5564)
|
1 year ago |
|
Georgi Gerganov
|
f3f28c5395
cmake : fix GGML_USE_SYCL typo (#5555)
|
1 year ago |
|
Pierrick Hymbert
|
e75c6279d1
server : enhanced health endpoint (#5548)
|
1 year ago |
|
Pierrick Hymbert
|
36376abe05
server : --n-predict option document and cap to max value (#5549)
|
1 year ago |
 Daniel Hiltgen
|
66c1968f7a
server : graceful server shutdown (#5244)
|
1 year ago |
|
Georgi Gerganov
|
1dcc3fde00
common : fix ub (#5530)
|
1 year ago |
 Herman Semenov
|
5d3de51f97
ggml, common, examples, tests : fixed type arguments in printf (#5528)
|
1 year ago |
|
Daniel Bevenius
|
fc0c8d286a
llava : update surgery script to not remove tensors (#5536)
|
1 year ago |
 Kawrakow
|
bd2d4e393b
1.5 bit quantization (#5453)
|
1 year ago |
 github-actions[bot]
|
c8e0d7efeb
flake.lock: Update
|
1 year ago |
|
Georgi Gerganov
|
8f1be0d42f
ggml : add ALiBi support for ggml_soft_max_ext (#5488)
|
1 year ago |
 Ananta Bastola
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
1 year ago |
 clibdev
|
d250c9d61d
gitignore : update for CLion IDE (#5544)
|
1 year ago |
|
Georgi Gerganov
|
5bf2b94dd4
cmake : fix VULKAN and ROCm builds (#5525)
|
1 year ago |
