b4424

llama : update llama_model API names (#11063)

* llama : deprecate llama_free_model, add llama_model_free

ggml-ci

* llama : change `llama_load_model_from_file` -> `llama_model_load_from_file`

ggml-ci

b4422

mmap : fix fileno macro clash (#11076)

* mmap : fix fileno macro clash

ggml-ci

* cont

ggml-ci

b4419

CUDA: add BF16 support (#11093)

* CUDA: add BF16 support

b4418

Vulkan: Add device-specific blacklist for coopmat for the AMD proprie…

b4417

llama : Add support for DeepSeek V3 (#11049)

* convert : extend DEEPSEEK2 model architecture to support DeepseekV3ForCausalLM by adding EXPERT_WEIGHTS_NORM and EXPERT_GATING_FUNC model parameters and FFN_EXP_PROBS_B tensor type

* vocab : add DeepSeek V3 pre-tokenizer regexes

* unicode : handle ACCENT_MARK and SYMBOL categories in regex

* llama : add DeepSeek V3 chat template, handle new model parameters and tensor types

---------

Co-authored-by: Stanisław Szymczyk <[email protected]>

b4416

[GGML][RPC] Support for models with non-512-aligned tensors over RPC.…

b4415

llama : add support for the cohere2 model architecture (#10900)

b4414

sync : ggml

b4411

fix: Vulkan shader gen binary path (#11037)

b4410

common : disable KV cache shifting automatically for unsupported mode…