b4151

CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)

* CANN Support Ascend310P to accelerate F32 and F16 Model

* Add compile option soc type macro ASCEND_310P to ggml-cann lib

* Remove unused code

* Remove the ascend soc_type hard code compile option in CMakelist.txt

b4099

scripts : fix missing key in compare-llama-bench.py (#10332)

b4066

metal : more precise Q*K in FA vec kernel (#10247)

b3798

Update CUDA graph on scale change plus clear nodes/params  (#9550)

* Avoid using saved CUDA graph if scale changes and reset nodes/params on update

Fixes https://github.com/ggerganov/llama.cpp/issues/9451

* clear before resize

b3755

ggml : ggml_type_name return "NONE" for invalid values (#9458)

When running on Windows, the quantization utility attempts to print the types that are not set which leads to a crash.

b3668

llama-bench : fix NUL terminators in CPU name (#9313)

b3639

vulkan : fix build (#0)

ggml-ci

b3358

Server: Enable setting default sampling parameters via command-line (…

b3277

Fix gemma2 tokenizer convert (#8244)

* fix gemma2 tokenizer convert

* remove scores

* improve code, fix new line issue

b2837

llava : fix moondream support (#7163)

* Revert "Revert "llava : add support for moondream vision language model (#6899)""

This reverts commit 9da243b36ac0b9d609adfaaa4c8f1cc8c592f737.

* Fix num_positions and embeddings initialization