b5494

server: fix regression on streamed non-chat completion w/ stops (#13785)

* more forgiving message diffs: partial stop words aren't erased, full stops are

* Add (slow) server test for completion + stream + stop

b5493

examples : allow extracting embeddings from decoder contexts (#13797)

ggml-ci

b5492

llama : clarify deprecation message (#13794)

b5490

vulkan: mark IM2COL as supporting non-contig (#13783)

b5489

CANN: Add the basic supports of Flash Attention kernel (#13627)

* cann: add the basic FA support

* cann: update the readme

* cann: update the FlashAttention with PSEShift

* cann: update the input parameters in FA

* cann: update the alibi with max_bias

* cann: add the constrints of softcap

* cann: update the docs CANN.md

* cann: update the docs CANN.md

* cann: fix typo of CANN.md

* cann: add some comments and update the CANN.md

* cann: update the CANN.md

* cann: update the inner precise for fusedInferAttention

* cann: update the constraints of flash_attn_ext on ggml-cann.cpp

* cann: clean the whitespace

* cann: clean the whitespace

* cann: add a new endline

b5488

`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3…

b5486

tests : improve UGM tokenizer test coverage (#13773)

b5484

rpc : Fix build on OpenBSD (#13541)

b5483

mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760)

* mtmd : add Qwen2-Audio support

* small clean up

* update discussion link

* clarify mtmd_get_output_embd

* clarification in multimodal.md

* fix ultravox bug

* ggml_cont

b5481

server: fix/test add_generation_prompt (#13770)

Co-authored-by: ochafik <[email protected]>