 Molly Sophia
|
912c331d3d
Fix merge error in #9454 (#9589)
|
1 year ago |
 Johannes Gäßler
|
a5b57b08ce
CUDA: enable Gemma FA for HIP/Pascal (#9581)
|
1 year ago |
 Shankar
|
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
|
1 year ago |
|
Molly Sophia
|
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
|
1 year ago |
 slaren
|
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
|
1 year ago |
 agray3
|
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
|
1 year ago |
 Huang Qi
|
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
|
1 year ago |
|
slaren
|
63351143b2
quantize : improve type name parsing (#9570)
|
1 year ago |
 Georgi Gerganov
|
d13edb17ed
ggml : fix builds (#0)
|
1 year ago |
|
Georgi Gerganov
|
27609c49b9
ggml : fix trailing whitespace (#0)
|
1 year ago |
|
Georgi Gerganov
|
4301535326
sync : ggml
|
1 year ago |
|
Johannes Gäßler
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
Georgi Gerganov
|
a6809c6a2e
examples : add null threadpool args where needed (ggml/0)
|
1 year ago |
|
Johannes Gäßler
|
5cb12f6839
CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562)
|
1 year ago |
|
Georgi Gerganov
|
d39e26741f
examples : flush log upon ctrl+c (#9559)
|
1 year ago |
 Sigbjørn Skjæret
|
722ec1eb51
perplexity : do not escape input data by default (#9548)
|
1 year ago |
|
Georgi Gerganov
|
6026da52d6
server : clean-up completed tasks from waiting list (#9531)
|
1 year ago |
|
Sigbjørn Skjæret
|
eca0fab44e
imatrix : disable prompt escape by default (#9543)
|
1 year ago |
|
slaren
|
64c6af3195
ggml : fix n_threads_cur initialization with one thread (#9538)
|
1 year ago |
|
Georgi Gerganov
|
0d2f22e45c
scripts : verify py deps at the start of compare (#9520)
|
1 year ago |
 Daniel Bevenius
|
6443ddd985
llama : use reserve/emplace_back in sampler_sample (#9534)
|
1 year ago |
 Vinesh Janarthanan
|
8a308354f6
server : match OAI structured output response (#9527)
|
1 year ago |
 Eric Zhang
|
f799155ab8
server : fix OpenSSL build (remove obsolete `LOG_INFO`) (#9529)
|
1 year ago |
 Neo Zhang Jianyu
|
faf67b3de4
[SYCL]set context default value to avoid memory issue, update guide (#9476)
|
1 year ago |
 Michael Podvitskiy
|
7be099fa81
llama-bench: correct argument parsing error message (#9524)
|
1 year ago |
 Bert Wagner
|
8b836ae731
arg : add env variable for parallel (#9513)
|
1 year ago |
|
Michael Podvitskiy
|
8344ef58f8
llama : fix n_vocab init for 'no_vocab' case (#9511)
|
1 year ago |
 Max Krasnyansky
|
0226613853
threadpool : skip polling for unused threads (#9461)
|
1 year ago |
 Yuri Khrustalev
|
503147a9f9
unicode : add <algorithm> (#9508)
|
1 year ago |
 Gabe Goodhart
|
0d2ec43833
llama : support IBM Granite architecture (#9412)
|
1 year ago |
