Releases: ggml-org/llama.cpp
Releases Β· ggml-org/llama.cpp
b5526
mtmd : move helpers to dedicated library (β οΈ breaking change) (#13866) * mtmd : move helpers to dedicated library * fix server build * rm leftover cmakelist code
b5524
llama : add support for BertForSequenceClassification reranker (#13858) * convert: add support for BertForSequenceClassification * add support for reranking using BertForSequenceClassification * merge checks of eos and sep * fix lint --------- Co-authored-by: dinhhuy <[email protected]>
b5522
server: fix remove 'image_url'/'input_audio' json-object effectlly foβ¦
b5519
CUDA: fix FA tg at long context for CC >= 8.9 (#13852)
b5517
CANN: Add SOC TYPE printing in cmake configuration (#13837)
b5516
opencl: add new ops - `argsort`, `div`, `sub`, `addrows`, `sigmoid`, β¦
b5515
opencl: mark `mul_mat` `f32f32` as supporting non-contiguous tensors β¦
b5514
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) Also change it to be controlled by an env var rather than cmake flag
b5513
cmake : add llama-cparams.cpp to build (#13832)
b5512
SYCL: add gelu_erf kernel (#13749) * SYCL: add gelu_erf kernel * refactor code Co-authored-by: Atharva Dubey <[email protected]> * Use scope_op_debug_print --------- Co-authored-by: Atharva Dubey <[email protected]>