model : refactor bias tensor variable names (#22079)

• refactor bias tensor variable names

• use create_tensor_qkv for jina-bert-v2

android : libcommon -> libllama-common (#22076)

ggml-backend-meta: add multi-segment read support in get_tensor (#22063)

ci : free disk space for rocm release (#22012)

ggml-webgpu: fix compiler warnings and refactor FlashAttention encoding (#21052)

• Update workflows to remove dependence on llvmpipe

• Try setting Dawn_DIR

• remove c++20 initializers

• Move to proper guid

• Try avoiding segfaults on vulkan backend process exit

• Remove compiler warnings on parameter casting

• Fix soft_max and update reg_tile accumulation to f32 for better precision

• Refactor flash_attn a bit

• remove c++20 initializers and format

• Increase div precision for NVIDIA

• revert div precision and comment out ggml-ci node for now

• Formatting

• Try debugging on a failing CI node

• Revert "Try debugging on a failing CI node"

This reverts commit 1971e33.

CUDA: use LRU based eviction for cuda graphs (#21611)

• CUDA: use a ring-buffer for cuda graphs

• bump limit to 128

• use LRU eviction

• better naming

• do periodic clean-up

ci : add android arm64 build and release (#21647)

• server: respect the ignore eos flag

• ci: add android arm64 build and release

• patch

• pin android-setup actions to v4

• Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret [email protected]

• lf in the suggestion

Co-authored-by: Sigbjørn Skjæret [email protected]

mtmd: add missing struct tag (#22023)

libs : rename libcommon -> libllama-common (#21936)

• cmake : allow libcommon to be shared

• cmake : rename libcommon to libllama-common

• cont : set -fPIC for httplib

• cont : export all symbols

• cont : fix build_info exports

• libs : add libllama-common-base

• log : add common_log_get_verbosity_thold()

model : Gemma4 model type detection (#22027)

• model : Gemma4 model type detection

• model : Gemma4 model type detection