Repository Issue Activity (beta)

#7593 Feature: FunASR/SenseVoice STT extension as Whisper alternative

#7628 llama cpp update to support the new Laguna architecture

#7629 "Continue" crashes with jinja2 UndefinedError when a single message exceeds the context size

#7626 Support for NVFP4 and make user aware about model compatability

#6772 Deepseek-R1 not doing reasoning, llama.cpp, "MemoryError"

#7621 Extension idea: BGPT scientific evidence tool for local research chat

#7620 Extension idea: BGPT scientific evidence lookup

#7619 Question: Best way to access text generation webui API from Southeast Asia?

#7606 error with the One-click installer

#7618 unknown model architecture: 'minimax-m3'

#7616 gemma4uv support in llama.cpp when?

#7613 Extension: dakera_memory — persistent cross-session semantic memory

#7612 Test

#7609 Feature request: SuperCompress prompt compression

#7607 Feature: Prompt compression to reduce context usage in LLM generation

#7608 UI area for tools

#7561 OpenAI-compatible API providers

#368 transformers error loading Llama

#7599 gptq/awq model loaders

#7594 DELETED!

#7603 Optimization suggestions for image handling when using VLMs

#4602 Recieving error when trying to load models

#7601 OpenAI API: Full spec conformity is achievable already

#7600 Token count display gets confused when switching chats

#7598 window11 5057打开软件后闪退