ngxson/llama.cpp

server: support OAI /v1/audio/transcriptions API (for AI review) examples server

[Mirror] https://github.com/ggml-org/llama.cpp/pull/21711 examples

[Mirror] feat: jinja engine improvements for reka-edge testing jinja parser

Xsn/mistral small 4 (for CI) python testing

convert_hf_to_gguf: fix flake8 E301 in Mistral4Model python

Xsn/mtmd debug (for CI) examples

[Mirror] llama: dynamic head_dim and n_rot for SWA python model

[Mirror] Parse port numbers from MCP server URLs in CORS proxy examples python server

[Mirror] server : fix router child env in containerized environments examples server

Jinja tests and `lstrip_block` fixes testing

jinja whitespace tests testing

fix(cuda): prevent UVM driver deadlock on SIGINT examples server

mimo2: wire RMS eps + MoE bias + converter guards python model

[Mirror] Support Youtu-VL Model examples python

Rebased ASR for LFM2-Audio-1.5B examples ggml python Nvidia GPU testing

Xsn/cli arrow left right

WebUI updates for llama-server model management feature examples ggml python server SYCL Nvidia GPU Vulkan testing devops model OpenCL

Allozaur/server model management v1 2 examples server

Allozaur/server model management v1 2 examples server

PoC router/proxy server examples server testing

FOR CI | common: move download functions to download.(cpp|h)

Mrope fix examples

ggml : refactor forward_dup for cpu backend ggml

Implement pixel unshuffle block for lfm2vl examples

ggml_scale_bias

Hunyuan tokenizer python

WIP Pixtral examples python

clip : use smart pointers examples

Llama-4 mapping python

llama4 WIP python