bandoti
|
d98f2a35fc
ci: disable LLAMA_CURL for Linux cross-builds (#13871)
|
7 ay önce |
Đinh Trọng Huy
|
e0e3aa231d
llama : add support for BertForSequenceClassification reranker (#13858)
|
7 ay önce |
Đinh Trọng Huy
|
aa6dff05be
convert: small addition to support LlamaModel (#13838)
|
7 ay önce |
Sky
|
c962ae3382
server: fix remove 'image_url'/'input_audio' json-object effectlly for 'llama_params' in multimodal-model-mode (#13853)
|
7 ay önce |
Xuan-Son Nguyen
|
a3938fb53d
convert : fix qwen omni conversion (#13859)
|
7 ay önce |
Alex Fanthome
|
f7873fc698
tests : change umlaut test (#11600)
|
7 ay önce |
Johannes Gäßler
|
a68247439b
CUDA: fix FA tg at long context for CC >= 8.9 (#13852)
|
7 ay önce |
Xuan-Son Nguyen
|
26b79b6cb3
convert : fix tensor naming conflict for llama 4 vision (#13836)
|
7 ay önce |
leo-pony
|
1e8659e65a
CANN: Add SOC TYPE printing in cmake configuration (#13837)
|
7 ay önce |
lhez
|
a3c30846e4
opencl: add new ops - `argsort`, `div`, `sub`, `addrows`, `sigmoid`, `group_norm` (#13787)
|
7 ay önce |
lhez
|
1701d4c54f
opencl: mark `mul_mat` `f32f32` as supporting non-contiguous tensors (#13790)
|
7 ay önce |
Jeff Bolz
|
bef8176387
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817)
|
7 ay önce |
Georgi Gerganov
|
34b7c0439e
cmake : add llama-cparams.cpp to build (#13832)
|
7 ay önce |
Akarshan Biswas
|
f3101a8cc6
SYCL: add gelu_erf kernel (#13749)
|
7 ay önce |
Georgi Gerganov
|
1c49c70d07
sync : ggml
|
7 ay önce |
Xuan-Son Nguyen
|
a8ea03d8ad
ggml : add ggml_repeat_4d (#13824)
|
7 ay önce |
xctan
|
05f6ac6283
ggml : riscv: add xtheadvector support (#13720)
|
7 ay önce |
Xuan-Son Nguyen
|
bc583e3c63
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)
|
7 ay önce |
bandoti
|
72b090da2c
docs: remove link for llama-cli function calling (#13810)
|
7 ay önce |
Christian Kastner
|
7fe03e7446
ggml-cpu: x86 feature detection is specific to x86 (#13811)
|
7 ay önce |
Diego Devesa
|
952f3953c1
ggml : allow CUDA graphs when using pipeline parallelism (#13814)
|
7 ay önce |
Georgi Gerganov
|
81713121ee
kv-cells : track min/max used cells and per-sequence positions (#13808)
|
7 ay önce |
Georgi Gerganov
|
f9cd68398b
sampling : make sure samplers return at least 1 token (#13822)
|
7 ay önce |
Georgi Gerganov
|
4f81b33e32
llama : validate seq id batch input (#13809)
|
7 ay önce |
Olivier Chafik
|
cdf94a1802
server: --offline mode (#13804)
|
7 ay önce |
Georgi Gerganov
|
a26c4cc11e
scripts : add option to compare commits in Debug (#13806)
|
7 ay önce |
Georgi Gerganov
|
4265a87b59
cuda : avoid cuGetErrorString (#13791)
|
7 ay önce |
Akarshan Biswas
|
6f180b915c
SYCL: Add non contiguous support in RMS_NORM and NORM kernels (#13611)
|
7 ay önce |
Olivier Chafik
|
03f582ae8f
server: fix streaming crashes (#13786)
|
7 ay önce |
standby24x7
|
88c125f2ac
examples/training: Fix file name in README (#13803)
|
7 ay önce |