textgen · Issues· 839 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #7628
llama cpp update to support the new Laguna architecture
enhancementUpdated Sep 14, 2026 - #7656
Bug: Empty JSON chat history files cause JSONDecodeError (very rare)
bugUpdated Sep 10, 2026 - #7598
window11 5057打开软件后闪退
bugUpdated Sep 5, 2026 - #7652
How to stream model from Disk to VRAM?
enhancementUpdated Aug 27, 2026 - #7650
Thinking wrongly preserved in chat-instruct mode with Gemma 4 template
bugUpdated Aug 27, 2026 - #7646
No think mode?
Updated Aug 22, 2026 - #7626
Support for NVFP4 and make user aware about model compatability
enhancementUpdated Aug 21, 2026 - #7593
Feature: FunASR/SenseVoice STT extension as Whisper alternative
Updated Jul 23, 2026 - #7629
"Continue" crashes with jinja2 UndefinedError when a single message exceeds the context size
bugUpdated Jul 22, 2026 - #6772
Deepseek-R1 not doing reasoning, llama.cpp, "MemoryError"
Updated Jul 16, 2026 - #7619
Question: Best way to access text generation webui API from Southeast Asia?
Updated Jul 12, 2026 - #7606
error with the One-click installer
bugUpdated Jul 10, 2026 - #7618
unknown model architecture: 'minimax-m3'
bugUpdated Jul 10, 2026 - #7616
gemma4uv support in llama.cpp when?
Updated Jul 8, 2026 - #7613
Extension: dakera_memory — persistent cross-session semantic memory
Updated Jul 1, 2026