Skip to content

Releases: ZipXuan/llama.cpp

b4130

19 Nov 11:43
a88ad00
Compare
Choose a tag to compare
llama : add OLMo November 2024 support (#10394)

* Add OLMo November 2024 constants

* Add OLMo November 2024 converter

* Add loading of OLMo November 2024 tensors and hyper parameters

* Add building of OLMo November 2024 model

b4127

19 Nov 05:11
557924f
Compare
Choose a tag to compare
sycl: Revert MUL_MAT_OP support changes (#10385)

b3804

23 Sep 03:58
c35e586
Compare
Choose a tag to compare
musa: enable building fat binaries, enable unified memory, and disabl…

b3802

22 Sep 13:09
a5b57b0
Compare
Choose a tag to compare
CUDA: enable Gemma FA for HIP/Pascal (#9581)

b3801

22 Sep 04:08
ecd5d6b
Compare
Choose a tag to compare
llama: remove redundant loop when constructing ubatch (#9574)

b3487

29 Jul 14:51
439b3fc
Compare
Choose a tag to compare
cuda : organize vendor-specific headers into vendors directory (#8746)

Signed-off-by: Xiaodong Ye <[email protected]>

b3486

29 Jul 08:50
0832de7
Compare
Choose a tag to compare
[SYCL] add conv support (#8688)

b3384

13 Jul 08:26
4e24cff
Compare
Choose a tag to compare
server : handle content array in chat API (#8449)

* server : handle content array in chat API

* Update examples/server/utils.hpp

Co-authored-by: Xuan Son Nguyen <[email protected]>

---------

Co-authored-by: Xuan Son Nguyen <[email protected]>